Publication
Identifying the Unknown With Clustering Metrics
https://www.toptal.com/developers/machine-learning/clustering-metrics-for-comparison
Surbhi is available for hire
Hire SurbhiSurbhi Gupta
Verified Expert in Engineering
Data Scientist and Machine Learning Developer
Jalpaiguri, West Bengal, India
Toptal member since November 2, 2021
Bio
Surbhi, previously a CTO at a GenAI startup and assistant professor at MUJ, is a generative AI, ML, and NLP expert with 5+ years of experience. She has designed and developed ML-based end-to-end solutions for startups at Toptal and Fortune 500 clients at Utopia. Her expertise includes ML, deep learning, NLP, computer vision, LLMs, GPT, AI, MLOps, and AWS. Surbhi solved problems in EAM, marketing, finance, chatbot, and crypto industries. She published research in robotics and optimization.
Portfolio
Freelance - Stealth Mode Startup
Agentic AI, AI Agents, AI Automation, AI Prompts, APIs...
Freelance | Stealth mode Startup
Agentic AI, AI Agents, Claude API, OpenAI, google ADK...
HelloFresh
Artificial Intelligence (AI), AI Consulting, Automation...
Experience
- Artificial Intelligence (AI) - 5 years
- Robotics - 5 years
- Machine Learning - 5 years
- Python - 5 years
- Generative Pre-trained Transformers (GPT) - 4 years
- Computer Vision - 4 years
- Natural Language Processing (NLP) - 4 years
- OpenAI - 3 years
Preferred Environment
Python, TensorFlow, Scikit-learn, OpenCV, Hugging Face, OpenAI, PyTorch, Amazon Web Services (AWS), Generative Pre-trained Transformers (GPT), Generative Artificial Intelligence (GenAI)
The most amazing...
...generative AI solution I've developed interacts with users to identify their brand's purpose and generates BVP and marketing content with text and images.
Work Experience
Full-stack & AI Developer
2026 - 2026
Freelance - Stealth Mode Startup
- Architected and delivered an end-to-end AI-powered multilingual education platform that transformed teacher-uploaded learning resources into structured lessons, bilingual content, interactive activities, and curriculum-aligned learning pathways.
- Designed and implemented agentic AI workflows, automating lesson planning, assessment creation, answer evaluation, personalized learning recommendations, and multimedia learning asset creation, including audio, video, flowcharts, images, and games.
- Developed prompt engineering frameworks that produced age-appropriate instructional content, assessments, and feedback with consistently structured outputs across diverse subjects and grade levels.
- Integrated multiple frontier language models, selecting models dynamically based on task complexity, quality requirements, and operational cost to improve overall system efficiency.
- Implemented cloud-native back-end services using Python and AWS to support scalable AI inference, document processing, user management, and content generation workflows.
- Engineered adaptive assessment capabilities that generated diagnostic, formative, and summative evaluations with varying cognitive difficulty levels, enabling personalized learning experiences based on student performance.
- Built an autonomous student-facing conversational agent that onboarded learners and guided daily study — recommending the next topic, explaining concepts on demand, and answering questions in context during a lesson.
- Gave the agent live context on the student's current screen, its capabilities, and the topic being taught, so it stayed in scope and constructively redirected off-topic requests back to the lesson.
- Enabled the agent to act in the product, not just reply — navigating students to the right screen and invoking tools mid-conversation to generate images, practice activities, and interactive quiz cards rendered inline in chat.
- Designed the agent's instructions and tool-selection logic, iterating on behavior by reviewing transcripts, and implemented real-time voice interaction over the Gemini Live API with TTS/STT.
Technologies: Agentic AI, AI Agents, AI Automation, AI Prompts, APIs, Amazon Web Services (AWS), Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI), Claude Code, Claude, Gemini, Image Generation, Audio, Gemini Live API, Infographics, Videos, Prompt Engineering, Cloud Deployment, Web Development, Software as a Service (SaaS), SaaS, Conversational AI, Conversational Design, Memory Management, RAG Systems, Agentic RAG Systems, Education Technology (Edtech), Prompt Optimization, Text-to-Speech (TTS), AI Voice Agents, Agentic AI Systems, Agentic Workflow Design, Solution Architecture, RAG Architecture, Speech-to-Text (STT), Software Architecture, AWS WAF, Google API, Consulting, IT Consulting, Data-informed Recommendations, Evaluation, Performance Optimization, Software Engineering, Back-end, Document Processing, Data Extraction, Google Document AI, PDF Scraping, Anthropic, PDF, Vector Databases, AI Agent Orchestration, Workflow Automation, API Development, Machine Learning (ML) APIs, OpenAI, Natural Language Understanding (NLU), Architecture, Vibe Coding, AI Systems, Multi-agent Orchestration, Multi-agent Systems, Full-stack, Localization, Dashboards, Dashboard Development, React, Node.js, TypeScript, Large Language Models (LLMs), Technical Architecture, AI Integration, System Architecture, Cloud Architecture, Technical Leadership, Scalability, Next.js, AI Model Integration, Web Applications, CSS, HTML, Integration, Reporting, ETL
Agentic AI Developer
2026 - 2026
Freelance | Stealth mode Startup
- Designed and developed an agentic AI application using Google ADK and Python to generate business intelligence questions by analyzing customer KPIs alongside external market factors, enabling structured exploration of performance drivers.
- Built an autonomous research agent capable of tool usage (code generation and web search) to answer complex business questions, iteratively refining queries to perform deeper KPI analysis and uncover actionable insights.
- Implemented an end-to-end AI workflow that transformed analytical findings into business-oriented reports, enabling stakeholders to move from raw data and questions to decision-ready insights.
Technologies: Agentic AI, AI Agents, Claude API, OpenAI, google ADK, Agent Development Kit (ADK), AI Prompts, Prompt Engineering, Claude Code, RAG Pipelines, Datasets, Prompt Optimization, Agentic AI Systems, Agentic Workflow Design, RAG Architecture, Model Context Protocol (MCP), Consulting, IT Consulting, Data-informed Recommendations, Recommendation Systems, Evaluation, Performance Optimization, Claude, AI Agent Orchestration, Workflow Automation, AI Systems, Multi-agent Orchestration, Multi-agent Systems, Data Visualization, Business Intelligence (BI), BI Reporting, Large Language Models (LLMs), Artificial Intelligence (AI), AI Integration, Reports, Integration, Reporting, ETL
AI Automation Consultant
2025 - 2025
HelloFresh
- Led cross-functional workshops with multiple teams to identify common and team-specific pain points, translating them into AI-driven productivity improvement opportunities.
- Defined and communicated AI use cases tailored to different business functions, enabling teams to adopt practical, role-specific productivity enhancements.
- Delivered enterprise training sessions on leveraging Gemini within GSuite (including Google Sheets), enabling employees to integrate AI tools into daily workflows and improve efficiency.
Technologies: Artificial Intelligence (AI), AI Consulting, Automation, Large Language Models (LLMs), Gemini, Consulting, IT Consulting, Training, AI Integration, Communication, Attention to Detail, Reporting
AI Developer
2024 - 2024
Front Porch Communications LLC
- Developed an innovative application to automatically curate and update newsletters. Leveraged LLMs to rewrite news and other informative articles with AI-generated images, ensuring that the content resonated with the interests of the target audience.
- Used AI to generate a daily special feature related to what's special on that date.
- Explored different LLMs like OpenAI, Claude, Amazon Titan, Mistral, and Llama for different AI operations.
- Used LLMs to classify news into several categories and to reject advertisements and other unwanted content.
- Orchestrated the development of a robust back-end infrastructure hosted on AWS, utilizing a diverse array of services, including Step Functions, EventBridge Scheduler, Bedrock, DynamoDB, Amplify, and Lambda functions.
- Implemented automated workflow processes using AWS Step Functions, enabling efficient content aggregation, transformation, and distribution. Ensured timely and fast delivery of the generated articles at a large scale.
- Integrated Google Programmable Search Engine API, News APIs, and Google Maps API into the application to augment its functionality and provide users with comprehensive and up-to-date information.
Technologies: Artificial Intelligence (AI), Generative Pre-trained Transformers (GPT), Large Language Models (LLMs), ChatGPT API, Claude, Workflow Automation & System Integration, OpenAI API, Generative Artificial Intelligence (GenAI), APIs, AI Agents, Feasibility Studies, Strategic Planning, AI Prompts, Prompt Engineering, API Integration, Large Language Model Operations (LLMOps), Function Calling, Tools, Bias Mitigation & Hallucination Reduction, Observability, Web Development, Data Curation, AI Programming, Data Engineering, AI Automation, Automation, ChatGPT Prompts, RSS Feeds, Data Integration, ChatGPT, OpenAI GPT-3 API, OpenAI GPT-4 API, Agentic AI, AI Model Training, Minimum Viable Product (MVP), Model Evaluation, Prompt Optimization, Data Annotation, Agentic AI Systems, Agentic Workflow Design, Solution Architecture, Software Architecture, Google API, Google Places API, Consulting, IT Consulting, Data-informed Recommendations, Recommendation Systems, Evaluation, Performance Optimization, Software Engineering, Claude API, Back-end, Data Extraction, Anthropic, AI Agent Orchestration, Workflow Automation, API Development, Machine Learning (ML) APIs, OpenAI, Real Estate, Natural Language Understanding (NLU), Architecture, AI Systems, Multi-agent Orchestration, Multi-agent Systems, Data Visualization, Dashboards, Dashboard Development, Technical Architecture, AI Integration, System Architecture, Cloud Architecture, Technical Leadership, Scalability, Team Management, AI Model Integration, Web Applications, Graphs, Data-informed Visual Design, Integration, Reporting, ETL, REST APIs
LLM Expert
2023 - 2024
Freelancing
- Developed an innovative application to automatically curate and update newsletters. Leveraged LLMs to rewrite news articles, ensuring that the content resonated with the unique characteristics and interests of the target audience.
- Used AI to generate dynamic weather reports for cities nationwide. Taking daily weather forecasts as input, the application wrote interesting weather reports tailored to each city's specific climate conditions.
- Orchestrated the development of a robust back-end infrastructure hosted on AWS, utilizing a diverse array of services including Step Functions, EventBridge Scheduler, Bedrock, DynamoDB, Amplify, and Lambda functions.
- Implemented automated workflow processes using AWS Step Functions, enabling efficient content aggregation, transformation, and distribution.
- Integrated Google Programmable Search Engine API, News APIs, and Google Maps API into the application to augment its functionality and provide users with comprehensive and up-to-date information.
Technologies: Artificial Intelligence (AI), Large Language Models (LLMs), Amazon Web Services (AWS), ChatGPT API, OpenAI, Amazon Bedrock AgentCore, Python, Data Scraping, OpenAI GPT-4 API, Open-source LLMs, Workflow Automation & System Integration, OpenAI API, Generative Artificial Intelligence (GenAI), APIs, Feasibility Studies, Strategic Planning, AI Prompts, Prompt Engineering, API Integration, Function Calling, Large Language Model Operations (LLMOps), Bias Mitigation & Hallucination Reduction, Observability, Web Development, Data Curation, AI Programming, Data Engineering, AI Automation, Automation, ChatGPT Prompts, RSS Feeds, Data Integration, ChatGPT, OpenAI GPT-3 API, Agentic AI, Prompt Optimization, Performance Optimization, Anthropic, AI Systems, Multi-agent Systems, Technical Architecture, AI Integration
Co-founder and CTO
2022 - 2023
Freelance Client
- Secured significant investment capital for a company in the SAFE round-through, effective investor engagement, and a clear explanation of the technology.
- Developed the first version of the product, meeting all key functionality requirements.
- Led a technical due diligence process, assessed by a renowned AI company and investors.
- Spearheaded the establishment of a talented team through effective interviewing and assessment methods.
- Utilized OpenAI models, effective prompt-engineering strategies, and few-shot learning to pioneer AI-led conversations with human users. Extracted valuable insights from these interactions and generated impactful marketing propositions.
- Designed a feedback mechanism to collect training data from field experts for fine-tuning the models.
Technologies: Amazon Web Services (AWS), AWS Amplify, Artificial Intelligence (AI), OpenAI GPT-3 API, User Feedback, Few-shot Learning, Vue, TypeScript, Large Language Models (LLMs), ChatGPT API, Workflow Automation & System Integration, OpenAI API, Generative Artificial Intelligence (GenAI), APIs, Feasibility Studies, Strategic Planning, Full-stack, AI Prompts, Prompt Engineering, API Integration, Large Language Model Operations (LLMOps), Function Calling, Tools, Bias Mitigation & Hallucination Reduction, Observability, Web Development, Data Curation, Bots, User Interface (UI), User Experience (UX), Chatbots, Chatbot Conversation Design, AI Programming, Data Engineering, AI Automation, Automation, ChatGPT Prompts, Data Integration, ChatGPT, OpenAI GPT-4 API, AI Chatbots, Agentic AI, Business Writing, Content Writing, Creative Writing, Software as a Service (SaaS), SaaS, Conversational AI, Conversational Design, Memory Management, Model Evaluation, Prompt Optimization, Solution Architecture, Leadership, Software Architecture, Data-informed Recommendations, Evaluation, Back-end, AI Agent Orchestration, Workflow Automation, API Development, Machine Learning (ML) APIs, OpenAI, Architecture, Training, AI Systems, Technical Architecture, AI Integration, CTO, System Architecture, Cloud Architecture, Technical Leadership, Next.js, Communication, Interviewing, Team Management, AI Model Integration, Web Applications, CSS, HTML, Integration, Reporting, REST APIs
GPT-3 Expert
2022 - 2023
Alec Beglarian
- Developed an MVP for email generation using OpenAI GPT-3 APIs.
- Developed the MVP on the AWS cloud platform, which is integrated with a database, storage, Lambda functions, Amazon SES, etc.
- Fine-tuned the OpenAI model for data correction to be used for email generation.
Technologies: Artificial Intelligence (AI), Deep Learning, OpenAI, ChatGPT, JavaScript, React, Generative Pre-trained Transformer 3 (GPT-3), Large Language Models (LLMs), Fine-tuning, ChatGPT API, Workflow Automation & System Integration, OpenAI API, Generative Artificial Intelligence (GenAI), Feasibility Studies, Strategic Planning, Full-stack, AI Prompts, Prompt Engineering, API Integration, Large Language Model Operations (LLMOps), Web Development, Data Curation, User Interface (UI), User Experience (UX), AI Programming, Data Engineering, AI Automation, Automation, ChatGPT Prompts, Data Integration, OpenAI GPT-3 API, APIs, AI Model Training, Minimum Viable Product (MVP), Solution Architecture, AWS WAF, Back-end, Data Extraction, Workflow Automation, Machine Learning (ML) APIs, AI Systems, Technical Architecture, AI Integration, Cloud Architecture, AI Model Integration, Integration, REST APIs
ML Developer
2022 - 2022
SimpliCapital LLC
- Deployed machine learning models with AWS cloud platform, using services like Lambda functions, Amazon SageMaker, Amazon SNS, Amazon S3, etc.
- Improved machine learning model performance for the prediction of financial data.
- Created Amazon SageMaker training and inference pipelines for ML models.
Technologies: Python, Jupyter, Amazon Web Services (AWS), Machine Learning Operations (MLOps), Machine Learning, Data Science, Node.js, Amazon SageMaker, Workflow Automation & System Integration, Strategic Planning, AI Programming, RMSE, Forecasting, Data Engineering, AI Automation, Automation, Data Integration, Datasets, AI Model Training, Software as a Service (SaaS), SaaS, Solution Architecture, HIPAA Compliance, Performance Optimization, Back-end, Data Pipelines, Workflow Automation, AI Systems, Data Modeling, Artificial Intelligence (AI), Technical Architecture, AI Integration, Cloud Architecture, Scalability, AI Model Integration, Integration, ETL
AI Specialist | NLP Python Developer
2022 - 2022
Toptal Client
- Improved the NLP solution to identify business prospects in financial data.
- Used BERT-based POS tagging to extract important features from large documents.
- Made the solution interpretable by identifying words used to mark sentences relevant to business prospects.
- Used a Hugging Face transformer model for semantic similarity analysis.
Technologies: Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), GPU Computing, Python, Semantics, Transformers, PyTorch, Large Language Models (LLMs), Retrieval-augmented Generation (RAG), Open-source LLMs, Generative Artificial Intelligence (GenAI), AI Programming, Data Engineering, AI Automation, Automation, Data Extraction, AI Systems, Artificial Intelligence (AI), AI Integration
AI Specialist | Python and ML Developer
2022 - 2022
Daylight
- Used OpenAI for solving Q&A and document query problems for a chatbot.
- Provided an open-source alternative to the OpenAI document query solution with better accuracy.
- Identified groups of chat clusters using agglomerative clustering based on semantic similarity.
Technologies: Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), OpenAI, Transformers, Clustering, Scikit-learn, Beautiful Soup, Web Scraping, Deep Learning, GPU Computing, Generative Pre-trained Transformer 3 (GPT-3), Data Analysis, Sequence Models, PyTorch, Large Language Models (LLMs), Retrieval-augmented Generation (RAG), Embeddings from Language Models (ELMo), Open-source LLMs, Statistics, Generative Artificial Intelligence (GenAI), Feasibility Studies, AI Prompts, Prompt Engineering, AI Programming, Data Engineering, AI Automation, Automation, RAG Pipelines, RAG Systems, Agentic RAG Systems, Performance Optimization, Data Extraction, Natural Language Understanding (NLU), Artificial Intelligence (AI), AI Integration
AI Specialist | Python and ML Developer
2021 - 2022
Freelance
- Performed stance detection and topic modeling on social media data, using unsupervised and semi-supervised methods.
- Fine-tuned a pre-trained seq2seq transformer model for custom summarization tasks.
- Used NLP performance evaluation metrics like BERTscore and ROUGE score for NLP tasks and achieved a score of 0.89 BERTscore on the summarization task.
Technologies: Machine Learning, Python, Scikit-learn, PyTorch, Transformers, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Transfer Learning, Sequence Models, Data Science, Graphics Processing Unit (GPU), BERT, Named-entity Recognition (NER), Entity Extraction, Matplotlib, LSTM, Classification, TensorFlow, Pandas, Artificial Intelligence (AI), Deep Learning, Time Series Analysis, Time Series, Data Analysis, GPU Computing, Clustering, Cloud, Large Language Models (LLMs), Fine-tuning, Embeddings from Language Models (ELMo), Statistics, Generative Artificial Intelligence (GenAI), X (formerly Twitter) API, AI Programming, RMSE, Recurrent Neural Networks (RNNs), Data Engineering, AI Automation, Automation, Text-to-text Transfer Transformer (T5), AI Integration, Graphs
Senior Data Science Engineer
2017 - 2021
Utopia
- Developed an end-to-end machine learning solution for information extraction from scanned documents and diagrams that brought a good deal to a Fortune 100 company. Deployed the project to the client as a cloud application.
- Built a solution to identify equipment classes from descriptions and tags, which was used to deliver services to several clients.
- Created a solution that enables identifying valid values from product descriptions in material master data used to deliver services to various clients.
- Developed a solution to identify different shapes, tables, and text in diagram images. This required the application of several computer vision, image processing, deep learning, and machine learning techniques.
- Built a Dialogflow voice interface with a custom "Hey 4C" wake word, designing intents and entities that routed spoken queries into our ML back end for description cleansing and equipment characteristic identification.
Technologies: Machine Learning, Deep Learning, Computer Vision, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Python, TensorFlow, Git, Streamlit, Optical Character Recognition (OCR), Scikit-learn, Image Processing, OpenCV, Convolutional Neural Networks (CNNs), NumPy, Amazon S3 (AWS S3), AWS Lambda, Tesseract, You Only Look Once (YOLO), Object Detection, Transfer Learning, Text Detection, Keras, Amazon Web Services (AWS), PyTorch, Cloud Deployment, Machine Learning Operations (MLOps), Named-entity Recognition (NER), Entity Extraction, SQL, Matplotlib, Algorithms, LSTM, Classification, Image Recognition, Pandas, Artificial Intelligence (AI), Data Analysis, Team Leadership, GPU Computing, Clustering, Cloud, Machine Vision, Code Review, Source Code Review, Technical Hiring, Interviewing, Data Scraping, PDF Scraping, Embeddings from Language Models (ELMo), Statistics, Data Curation, User Interface (UI), User Experience (UX), Flask, Amazon EC2, Kubernetes, AI Programming, RMSE, Recurrent Neural Networks (RNNs), Data Engineering, AI Automation, Automation, Data Integration, APIs, Datasets, Data Annotation, Solution Architecture, Leadership, Amazon EKS, HIPAA, HIPAA Compliance, Software Architecture, Software Engineering, Back-end, Data Pipelines, Document Processing, Data Extraction, Amazon Textract, PDF, Workflow Automation, API Development, Machine Learning (ML) APIs, Dialogflow, Architecture, Training, AI Systems, Data Visualization, Dashboards, Dashboard Development, Data Modeling, PostgreSQL, Technical Architecture, AI Integration, System Architecture, Cloud Architecture, Technical Leadership, Scalability, Attention to Detail, Team Management, Graphs, Data-informed Visual Design, Reports, Team Mentoring, Mentorship, Integration, Reporting, ETL
Assistant Professor
2017 - 2017
Manipal University Jaipur
- Lectured subjects like robotics and mechatronics system design, including topics on machine learning, artificial intelligence, and sensors.
- Conducted laboratory experiments to give students hands-on experience on MATLAB, control systems, and sensors.
- Conducted term papers and online quizzes and evaluated the performance of the students.
Technologies: Robotics, Machine Learning, Mechatronics, University Teaching, Matplotlib, Algorithms, Scikit-learn, Code Review, Interviewing, Communication, Attention to Detail
Senior Research Fellow
2012 - 2016
CSIR-Central Scientific Instruments Organisation
- Optimized the design of a minimally invasive surgical robotic arm and formulated the kinematic control for trajectory tracking by its end-effector. Published two papers on this work.
- Improved the design of a passive bipedal robot and underactuated it in simulation to walk stably on steep slopes of zero to 30 degrees. Published two papers on this work.
- Taught subjects like industrial control and robotics to diploma-level students.
Technologies: Robotics, Python, Control Systems, Underactuation, Research, Matplotlib, Algorithms, Classification, Scikit-learn, OpenCV, Artificial Intelligence (AI), Computer Vision, Time Series Analysis, Time Series, Statistics, RMSE, Forecasting, Data Pipelines, Attention to Detail, Written Communication, Graphs, Data-informed Visual Design
Experience
A Brief Review of Dynamics and Control of Underactuated Biped Robots
This paper summarizes various designs, models, and control strategies used to enable stable walking and running for underactuated biped robots. I was the first author of this publication to work on literature surveys and writing.
The article is available at the following link: https://www.tandfonline.com/doi/full/10.1080/01691864.2017.1308270
The article is available at the following link: https://www.tandfonline.com/doi/full/10.1080/01691864.2017.1308270
Split Compound Words
https://github.com/droid-surbhi/split-compound-wordsDeveloped and published a GitHub repository for splitting compound words in a text-line into a collection of English dictionary words. If non-English text is given, then an option to first translate to English is also available.
Fake Vs. Real News Classification
https://www.kaggle.com/surbhig/classification-fake-vs-news-95-accuracyI created and published a Kaggle notebook to classify a given news paragraph into fake vs. real, with 95% accuracy. Kaggle dataset for fake vs. real news was used for training and testing. I used the multinomial Naive Bayes for classification and TF-IDF for feature vectorization.
Optimization Using Meta-heuristics
https://github.com/droid-surbhi/OptimizationI developed and published a GitHub repository for optimization using popular metaheuristics like tabu search and artificial bee colony optimization (ABC). Tabu search was written from scratch in MATLAB, while ABC was written in Python and is a modified version of the code published by the original author of the algorithm. The modifications were made to enable constrained integer optimization using ABC.
Design Optimization of Minimally Invasive Surgical Robot
We optimized the design within three degrees of freedom serial robotic arm to operate as a minimally invasive robotic surgery (MIRS) arm and attain multiple adjacent possible orifice locations, through which a planar workspace of prespecified geometry can be traced. To achieve this goal, we developed an algorithm to relate the design of such a MIRS arm to the possible orifice positions. The optimization problem was solved using several metaheuristics such as simulated annealing, Tabu search, artificial bee colonization, and genetic algorithm, and their performance was compared.
LighVe: Music Synced Lights
LighVe is a set composed of light strips and a mobile app. LighVe can pick up any music that is being played in the room and synchronize the light visualizations with its beats. I worked on the hardware, circuit design, electronics, and app design while another collaborator developed the backend.
Kinematic Control of An Articulated Minimally Invasive Surgical Robotic Arm
https://ieeexplore.ieee.org/document/7853054We created geometric transformations based on the constraints acting on the end-link coupled with kinematic-relations obtained using conventional techniques were used to drive a simulated 6-DOF general articulated robotic arm for minimally-invasive operations. This simulated arm verified the method by tracing predefined planar and 3D trajectories.
Clustering Utilities
https://github.com/droid-surbhi/clusteringThis repository contains the implementation of new clustering methods and utilities based on recent research papers. For example, incremental agglomerative clustering, given old clusters, maps new data to old clusters, creates new clusters for the unmapped records.
Resume Classification
https://github.com/droid-surbhi/resume_classificationUnsupervised classification of candidate resumes into testing, development, and management categories using Python.
• It uses latent Dirichlet allocation for topic modeling and counts vectorizer for vectorization.
• It also visualizes groups using Word Cloud.
• It uses latent Dirichlet allocation for topic modeling and counts vectorizer for vectorization.
• It also visualizes groups using Word Cloud.
Algorithm Design
https://github.com/droid-surbhi/algorithm_designThis program allows users to practice problems on algorithm design with solutions and explanations. It includes topics like recursion, sorting, trees, graph search, dynamic programming, and problems asked in screening processes.
Motion Planning
This explores various motion planning algorithms useful in robot motion, including simple motion techniques such as a rapidly exploring random tree (RRT), Dijkstra's algorithm for the shortest path, probabilistic roadmaps (PRM), and more.
Visiting Card Creator
https://chatgpt.com/g/g-jjCYHUH5o-visiting-card-creatorA ChatGPT assistant that provides visiting card designs. The assistant suggests the design based on the user's request with details like purpose, profession, etc. It also creates the images with the suggested design.
Character Imitation by AI: Professor Dumbledore
https://chatgpt.com/g/g-LI8gD4kNS-professor-dumbledoreThis ChatGPT assistant talks to the user like Professor Dumbledore from the movie and book series Harry Potter. It imitates the wise, philosophical manner in which the character used to talk in the series.
Data Analysis with 1nb.ai
Built an AI/LLM-based solution that, given tabular data, interactively analyzes it in IPython Notebook, uses interaction to understand user's requirements, provides valuable insights through data analysis and machine learning (ML), and creates documentation. Built an AI chatbot that retrieves the relevant notebook and generates answers to user queries.
LLM Chains with GraphQL
Worked on AI development to provide users with an interface to use advanced prompting based on question decomposition and least-to-most prompting with reasoning to improve LLM's output. It allows the user to use different LLM models in a single GraphQL query in LLM chains.
Learning Assistant
https://chatgpt.com/g/g-RpP03sU17-learningcastleEngineered an AI assistant designed to engage users in learning based on age and interests. I utilized an interactive role-playing game format to facilitate concept comprehension, weaving educational content into engaging quests reminiscent of Dungeons and Dragons.
Get Detailed Answers for Any Query with Interactive Documents Powered By LLMs
A web application that provides answers to users' queries in a friendly, guided manner with an interactive interface. Queries can be related to any field, such as analytical, coding, DIY, food, research, etc. It provides features like web search, different styles, and customization. It is powered by multiple large language models (LLMs), e.g., Gemini, Deep Seek, and Claude.
AI-powered Nutrition & Wellness Platform
http://planmyplate.todayA full-stack nutrition tracking web application that transforms how users understand their diet. PlanMyPlate uses vivid visual dashboards—a color-coded "nutrition wheel," "nutrition rainbow," and "food diversity" score—to help users instantly see what's working and what's missing in their meals.
WORK DONE
• Built an AI-powered recipe ingestion pipeline supporting 4 input methods: manual text entry, community dish library, URL-based recipe import, and photo-based OCR.
• Engineered a hybrid nutrition database layer that combines USDA FoodData Central and IFCT (Indian Foods Composition Tables) with AI-based gap-filling to produce confidence-labeled, transparent nutritional estimates.
• Designed and implemented real-time nutrient analytics—macronutrient breakdowns, bioavailability insights (what the body can actually absorb and optimal food pairings), and dual-direction deficiency/toxicity alerts.
• Built a community-driven dish platform that allows users to share, reuse, and import dishes, building a crowdsourced database of Indian and global cuisine.
• Delivered a PWA with Google Sign-in.
• Built an interactive data visualization layer for day-level nutrient completeness, food group diversity, and color-spectrum coverage.
WORK DONE
• Built an AI-powered recipe ingestion pipeline supporting 4 input methods: manual text entry, community dish library, URL-based recipe import, and photo-based OCR.
• Engineered a hybrid nutrition database layer that combines USDA FoodData Central and IFCT (Indian Foods Composition Tables) with AI-based gap-filling to produce confidence-labeled, transparent nutritional estimates.
• Designed and implemented real-time nutrient analytics—macronutrient breakdowns, bioavailability insights (what the body can actually absorb and optimal food pairings), and dual-direction deficiency/toxicity alerts.
• Built a community-driven dish platform that allows users to share, reuse, and import dishes, building a crowdsourced database of Indian and global cuisine.
• Delivered a PWA with Google Sign-in.
• Built an interactive data visualization layer for day-level nutrient completeness, food group diversity, and color-spectrum coverage.
Education
2010 - 2012
Master's Degree in Mechatronics
Indian Institute of Engineering Science and Technology - Kolkata, India
2005 - 2009
Bachelor's Degree in Electronics and Communication Engineering
Bundelkhand University - Jhansi, India
Certifications
AUGUST 2026 - PRESENT
Claude 101
Anthropic Education
NOVEMBER 2025 - PRESENT
Agentic AI
Deeplearning.AI
JANUARY 2025 - PRESENT
Building Agentic RAG with LlamaIndex
DeepLearning.AI
MAY 2022 - MAY 2025
AWS Certified Cloud Practitioner
Amazon Web Services
FEBRUARY 2022 - PRESENT
Introduction to Containers
AWS
JANUARY 2022 - PRESENT
Introduction to AWS Elastic Beanstalk
AWS
JANUARY 2022 - PRESENT
Sequence Models
DeepLearning.AI
APRIL 2021 - PRESENT
Introduction to Tensorflow for Artificial Intelligence, Machine Learning, and Deep Learning
DeepLearning.AI | via Coursera
AUGUST 2020 - PRESENT
Git Complete: The Definitive, Step-by-step Guide to Git
Udemy
MAY 2019 - PRESENT
Neural Networks and Deep Learning
DeepLearning.AI | via Coursera
AUGUST 2015 - PRESENT
6.00.1x: Introduction to Computer Science and Programming Using Python
MITx
MARCH 2014 - PRESENT
Control of Mobile Robots
Coursera
JULY 2013 - PRESENT
Machine Learning
Coursera
Skills
Libraries/APIs
Pandas, PyTorch, LSTM, OpenAI API, Claude API, Google API, Google Places API, API Development, REST APIs, TensorFlow, Scikit-learn, OpenCV, Keras, Matplotlib, React, AWS Amplify, Node.js, Vue, X (formerly Twitter) API, NumPy, Beautiful Soup
Tools
Git, ChatGPT, AI Prompts, Claude, Claude Code, Named-entity Recognition (NER), Amazon EKS, Amazon Textract, Visual Language Models (VLMs), MATLAB, You Only Look Once (YOLO), Amazon SageMaker, Confluence, OpenAI Gym, Jupyter, DeepSeek, Dialogflow
Languages
Python, SQL, TypeScript, CSS, HTML, C++, JavaScript, Python 3
Frameworks
Streamlit, LlamaIndex, Flask, AWS Serverless Application Model (SAM), Next.js
Paradigms
Automation, Model Context Protocol (MCP), Data-informed Visual Design, ETL, HIPAA Compliance, Business Intelligence (BI)
Storage
Data Integration, Data Pipelines, Amazon S3 (AWS S3), PostgreSQL, Cloud Deployment, Google Cloud, Amazon DynamoDB, Databases, PostgreSQL 10
Platforms
AWS Lambda, Amazon Web Services (AWS), Amazon EC2, Docker, AWS Elastic Beanstalk, Kubernetes
Other
Robotics, Artificial Intelligence (AI), Machine Learning, Deep Learning, Computer Vision, Natural Language Processing (NLP), Optical Character Recognition (OCR), Image Processing, Neural Networks, Tesseract, Data Science, Research, Entity Extraction, Classification, Image Recognition, Data Analysis, OpenAI, Team Leadership, Machine Vision, Code Review, Interviewing, Large Language Models (LLMs), Data Visualization, Generative Pre-trained Transformers (GPT), OpenAI GPT-3 API, Chatbots, Fine-tuning, ChatGPT API, Retrieval-augmented Generation (RAG), OpenAI GPT-4 API, PDF Scraping, Embeddings from Language Models (ELMo), Prompt Engineering, Gemini, Workflow Automation & System Integration, Generative Artificial Intelligence (GenAI), APIs, Feasibility Studies, Full-stack, Chatbot Conversation Design, AI Programming, RMSE, Recurrent Neural Networks (RNNs), Forecasting, Data Engineering, AI Automation, ChatGPT Prompts, AI Chatbots, Agentic AI, AI Model Training, Datasets, Software as a Service (SaaS), SaaS, Conversational AI, Conversational Design, Agentic RAG Systems, Model Evaluation, Prompt Optimization, Agentic AI Systems, Agentic Workflow Design, Solution Architecture, RAG Architecture, Software Architecture, Consulting, IT Consulting, Data-informed Recommendations, Evaluation, Performance Optimization, Software Engineering, Back-end, Document Processing, Data Extraction, Google Document AI, Anthropic, PDF, AI Agent Orchestration, Workflow Automation, Machine Learning (ML) APIs, Natural Language Understanding (NLU), Architecture, Vibe Coding, Training, AI Systems, Multi-agent Orchestration, Multi-agent Systems, Localization, Dashboards, Dashboard Development, Data Modeling, Technical Architecture, AI Integration, System Architecture, Cloud Architecture, Technical Leadership, Scalability, Communication, Attention to Detail, AI Model Integration, Web Applications, Graphs, Reports, Integration, Reporting, University Teaching, Control Systems, Underactuation, Convolutional Neural Networks (CNNs), Object Detection, Transfer Learning, Text Detection, Machine Learning Operations (MLOps), Graphics Processing Unit (GPU), Transformers, BERT, Sequence Models, Algorithms, Time Series Analysis, Time Series, Generative Pre-trained Transformer 3 (GPT-3), GPU Computing, Cloud, Source Code Review, Technical Hiring, Minimum Viable Product (MVP), Amazon Bedrock AgentCore, Open-source LLMs, Statistics, Multistage LLM Chains, AI Agents, Strategic Planning, API Integration, Large Language Model Operations (LLMOps), Bias Mitigation & Hallucination Reduction, Observability, Web Development, Data Curation, Bots, User Interface (UI), User Experience (UX), Function Calling, Tools, RAG Pipelines, Creative Writing, Memory Management, RAG Systems, Education Technology (Edtech), Text-to-Speech (TTS), AI Voice Agents, Text-to-text Transfer Transformer (T5), Leadership, FastAPI, Speech-to-Text (STT), HIPAA, AWS WAF, Recommendation Systems, Vector Databases, Mobile Apps, BI Reporting, Supabase, CTO, Written Communication, Team Management, Team Mentoring, Mentorship, Mechatronics, Optimization, Metaheuristics, Robot Operating System (ROS), Gated Recurrent Unit (GRU), Containers, Technical Writing, Publication, Simulations, Mathematics, Clustering, Web Scraping, Semantics, Generative Adversarial Networks (GANs), Hugging Face, Unsupervised Learning, Topic Modeling, DALL-E, User Feedback, Few-shot Learning, Motion Planning, Data Scraping, Recursion Testing, A/B Testing, Serverless, RSS Feeds, AI Suite, AI Consulting, google ADK, Agent Development Kit (ADK), Image Generation, Audio, Gemini Live API, Infographics, Videos, Business Writing, Content Writing, Gemini API, Data Annotation, Real Estate
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring