Siddharth is currently unavailable
Siddharth Deshpande
Verified Expert in Engineering
Data Scientist and Developer
Cambridge, United Kingdom
Toptal member since June 27, 2022
Bio
Siddharth is an interdisciplinary researcher with unique perspectives derived from translational projects and his combined educational background in materials engineering, biochemistry, healthcare, natural language processing (NLP), and data science. He has extensive experience working with biological structured and unstructured data and using state-of-art AI techniques to solve complex healthcare problems.
Portfolio
Norstella
Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI)...
Immersely
Amazon Web Services (AWS), Machine Learning, Game AI, Emotion Recognition...
Post Urban Ventures
Python, CTO, Deep Learning, Entrepreneurship, Pitch Preparation...
Experience
- Healthcare - 6 years
- Python - 6 years
- Data Science - 5 years
- Generative Pre-trained Transformers (GPT) - 5 years
- Pharmacology - 5 years
- Natural Language Processing (NLP) - 5 years
- Data Visualization - 4 years
- Analytics - 3 years
Work Experience
GenAI Consultant
2023 - PRESENT
Norstella
- Engaged as a specialist consultant to develop a GenAI‑powered pharmaceutical consulting chatbot for the Norstella group, enabling queries across diverse databases and datasets held by Norstella‑affiliated companies.
- Integrated diverse datasets encompassing a broad spectrum, including patents, scholarly articles, documents on mergers and acquisitions, clinical trials, FDA‑related materials, and Snowflake databases.
- Designed and implemented the chatbot architecture using advanced libraries such as Guidance, Sglang, and Langchain to ensure robust and efficient functionality.
- Developed the initial version of the chatbot, successfully launched for internal use, resulting in significant cost savings of approximately 2 million pounds by reducing consultation hours for the analysts.
Technologies: Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI), Natural Language Processing (NLP), Healthcare IT, AWS IoT, Analytics
Chief Technological Officer (Interim)
2022 - PRESENT
Immersely
- Worked for Immersely, which was building a platform to unlock the ability for game developers to create hyper-personalized games that adapt in real time to player emotion, boosting engagement to create better, more commercially successful games.
- Took charge of developing ML models that use physiological signals to detect the emotions of a person while he is gaming to develop an interactive gaming experience.
- Tasked with developing a technical roadmap and back-end tech infrastructure for the company.
Technologies: Amazon Web Services (AWS), Machine Learning, Game AI, Emotion Recognition, Python 3, Data Science, LangChain
Deep Tech Venture Builder
2022 - PRESENT
Post Urban Ventures
- Validated technological feasibility of new startup ideas before funding, built technical prototypes (MVP) for pre-seed and seed round investor pitches, and supported early-stage startups with essential technical infrastructure.
- Worked as an interim CTO of four startups and as a technical advisor for two startups within Post Urban Ventures.
- Contributed to securing a £5 million grant in funding for startups successfully.
- Involved in preparing technical pitch decks, offered expert advice and guidance, and helped promote startup success. Designed technical roadmaps for scaling startups after pre-seed and seed rounds.
Technologies: Python, CTO, Deep Learning, Entrepreneurship, Pitch Preparation, Artificial Intelligence (AI), Web Scraping, Data Science, Excel Expert, JSON, Interactive Charts, CSV File Processing, Language Models, Unstructured Data Analysis, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Machine Learning, Healthcare, Chatbots, Chatbot Conversation Design, OpenAI, LangChain, Weaviate, Pinecone
Senior AI/ML and NLP Chatbot Developer
2023 - 2023
Richmond Ayirebide
- Developed an accountant chatbot based on the client's requirements using ChatGPT, finetuned GPT-3, and Telegram.
- Streamlined the preprocessing and postprocessing to format results into easy-to-view Excel sheets for the client.
- Helped set up a plan for the future deployment of the chatbot into the cloud infrastructure.
Technologies: Natural Language Processing (NLP), Python, Chatbots, Machine Learning, Generative Pre-trained Transformers (GPT), Artificial Intelligence (AI), Deep Learning, Chatbot Conversation Design, OpenAI, LangChain, Weaviate, Pinecone
Chief Technological Officer (Interim)
2022 - 2022
Bioleap
- Brought on board to develop the technical framework for Bioleap, a startup focused on developing AI-based single-cell models.
- Managed the building of cloud capabilities in AWS, hired a competent technical team, and improved the current mechanistic models.
- Established several strategic technological partnerships with leading bio-modeling labs. Built a cloud-based automation strategy for Bioleap models.
- Established a technology strategy (tech stack), technical roadmap, and business plan to support the growth strategy.
Technologies: Artificial Intelligence (AI), Bioinformatics, Single-cell Modeling, Time Series Analysis, Computational Biology, Excel Expert, JSON, Interactive Charts, CSV File Processing, Language Models, Unstructured Data Analysis, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Machine Learning, Python, Healthcare, Data Science, CTO, Medical Diagnostics
NLP Data Scientist
2021 - 2022
Evaluate Ltd
- Developed a press-release classifier that categorizes news articles into 40 technology classes, saving the company around 30,000 pounds per year in third-party API licenses.
- Identified digital health innovations from clinical trials, news articles, and deal documents for a custom analytics project that reduced workforce hours of manual document classification for a Japanese client.
- Created a core NLP framework to extract biomedical entities from unstructured texts and visualize them as a graphical network; the framework became popular for discovering new biomedical relations and was subsequently used in many Evaluate products.
Technologies: Python, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Amazon Web Services (AWS), Pharmacology, R&D, Data Science, Data Visualization, Machine Learning, Biomedical Skills, Bioinformatics, Microsoft Excel, Healthcare, Excel Expert, JSON, Interactive Charts, CSV File Processing, Language Models, Unstructured Data Analysis, Artificial Intelligence (AI), Spark NLP, PySpark, Spark ML, Chatbots
Data Scientist
2019 - 2021
Patsnap
- Developed PatSnap Bio, a core product that is one of the largest sequence searching platforms and is actively being used by large pharmaceutical companies.
- Created PatSnap Materials, another core product under Beta testing in China.
- Engaged actively in the product development and client feedback process for PatSnap Bio and PatSnap Materials.
- Filed five patent applications involving my technology.
Technologies: Python, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Analytics, Patents, Product Development, Biology, Pharmacology, Composite Materials, Biomaterial, Engineering, Bioinformatics, Web Scraping, Machine Learning, Microsoft Excel, Data Science, Healthcare, Excel Expert, JSON, Interactive Charts, CSV File Processing, Language Models, Unstructured Data Analysis, Artificial Intelligence (AI), Spark NLP, PySpark, Spark ML
Project History
COVID-19 Scientific Journals Analysis
https://github.com/siddharth0112358/coronavirus_19Analyzed the COVID-19 dataset, a collection of scientific papers related to COVID-19, using different NLP techniques. The aim of the project was to get different insights using different NLP algorithms that might help understand research papers better.
Research papers available on GitHub:
• AutoDetect_COVID_FakeNews - Classification model for detecting Fake news regarding COVID
• BERT_semantic_search - Semantic search which finds similar sentences in COVID corpus in response to query question
• Biorelated_sentence_extraction_COVID - extract bio-related sentences from COVID corpus
• COVID_19_topic_modelling_Top2Vec - Topic modelling on COVID_19 corpus using Top2Vec
• COVID_explore_drugs - Explore drugs in the COVID corpus
• CoVID19_Ques_and_Ans - Covid papers Questions and Answering system based on doc2vec
• CoVID_19_NER_text_summarization_and_topic_modelling - BART summarization and LDA topic modelling and NER
• Covid_19_genome_analysis - COVID_19 genome analysis
• Covid_paper_rank_display - NER and covid papers recovery based on topic
• Medical_NER_Corona - NER on coronavirus dataset
• Mining_COVID_keywords - mining keywords using bigrams and trigrams
Research papers available on GitHub:
• AutoDetect_COVID_FakeNews - Classification model for detecting Fake news regarding COVID
• BERT_semantic_search - Semantic search which finds similar sentences in COVID corpus in response to query question
• Biorelated_sentence_extraction_COVID - extract bio-related sentences from COVID corpus
• COVID_19_topic_modelling_Top2Vec - Topic modelling on COVID_19 corpus using Top2Vec
• COVID_explore_drugs - Explore drugs in the COVID corpus
• CoVID19_Ques_and_Ans - Covid papers Questions and Answering system based on doc2vec
• CoVID_19_NER_text_summarization_and_topic_modelling - BART summarization and LDA topic modelling and NER
• Covid_19_genome_analysis - COVID_19 genome analysis
• Covid_paper_rank_display - NER and covid papers recovery based on topic
• Medical_NER_Corona - NER on coronavirus dataset
• Mining_COVID_keywords - mining keywords using bigrams and trigrams
Alibaba Cloud Global AI Innovation Challenge
Won an Innovation Award for the project.
The goal of my project was to analyze the effect of weather on energy generation and demand and find a solution that can predict renewable energy generation and energy demand using weather parameters.
SOLUTION HIGHLIGHTS
• Solar, wind, and hydro energy generation prediction using climate and time parameters.
• Energy demand prediction was done using time and energy parameters (Model 1) and time, energy, and climate parameters (Model 2). Model 2 showed slightly higher accuracy than Model 1. It shows that climate parameters do not affect energy demand as significantly as energy parameters.
• Energy price prediction was done using time and energy parameters (Model 1) and time, energy, and climate parameters (Model 2). Model 2 showed higher accuracy than Model 1. It shows that climate parameters affect energy prices significantly.
For all the above cases, 10 million regression algorithms were tested. The ExtraTreeRegressor algorithm showed the best performance and was used to build the regression model.
URL: https://www.alibabacloud.com/blog/project-showcase-%7C-effect-of-weather-on-energy-generation-and-demand_598252
The goal of my project was to analyze the effect of weather on energy generation and demand and find a solution that can predict renewable energy generation and energy demand using weather parameters.
SOLUTION HIGHLIGHTS
• Solar, wind, and hydro energy generation prediction using climate and time parameters.
• Energy demand prediction was done using time and energy parameters (Model 1) and time, energy, and climate parameters (Model 2). Model 2 showed slightly higher accuracy than Model 1. It shows that climate parameters do not affect energy demand as significantly as energy parameters.
• Energy price prediction was done using time and energy parameters (Model 1) and time, energy, and climate parameters (Model 2). Model 2 showed higher accuracy than Model 1. It shows that climate parameters affect energy prices significantly.
For all the above cases, 10 million regression algorithms were tested. The ExtraTreeRegressor algorithm showed the best performance and was used to build the regression model.
URL: https://www.alibabacloud.com/blog/project-showcase-%7C-effect-of-weather-on-energy-generation-and-demand_598252
Conversational Chatbots
I built three conversational chatbots across different conversation channels, including Slack, WhatsApp, Dashboard, Discord, Telegram, and Facebook messenger. I developed chatbots using GPT-3 with additional constraints and prompt engineering.
• Conversation helper - This bot helps to simulate tough conversations so that the clients can practice the conversations beforehand. The client is scored on 2-3 conversation skills, and a report is generated at the end that shows his score and how to improve his conversation ability.
• Fashion assistant - This bot recommends fashion items based on client needs and stock inventory of the business. It uses a combination of GPT-3 and DALL-E.
• Google bot - This bot has a Google search engine capability and acts as an advisor/friend to whom you can ask any questions, and it will run a Google search in the back end to provide you with the most updated answers.
Bot previews can be shown during interviews.
• Conversation helper - This bot helps to simulate tough conversations so that the clients can practice the conversations beforehand. The client is scored on 2-3 conversation skills, and a report is generated at the end that shows his score and how to improve his conversation ability.
• Fashion assistant - This bot recommends fashion items based on client needs and stock inventory of the business. It uses a combination of GPT-3 and DALL-E.
• Google bot - This bot has a Google search engine capability and acts as an advisor/friend to whom you can ask any questions, and it will run a Google search in the back end to provide you with the most updated answers.
Bot previews can be shown during interviews.
Education
2016 - 2019
Doctorate in Medicine
National University of Singapore - Singapore
2014 - 2015
Master's Degree in Materials Science and Engineering
National University of Singapore - Singapore
2010 - 2014
Bachelor's Degree in Metallurgy and Material Science
College of Engineering Pune - Pune, India
Certifications
JANUARY 2023 - PRESENT
Healthcare NLP for Data Scientists
John Snow Labs
JANUARY 2023 - PRESENT
Spark NLP for Data Scientists
John Snow Labs
MAY 2022 - PRESENT
TensorFlow: Advanced Techniques Specialization
DeepLearning.AI | via Coursera
APRIL 2022 - PRESENT
Deep Learning for Healthcare Specialization
University of Illinois at Urbana-Champaign | via Coursera
MARCH 2022 - PRESENT
Customizing Your Models with TensorFlow 2
Imperial College London | via Coursera
MARCH 2022 - PRESENT
Generative Adversarial Networks (GANs) Specialization
DeepLearning.AI | via Coursera
JULY 2021 - PRESENT
Deployment of Machine Learning Models
Udemy
FEBRUARY 2021 - PRESENT
Natural Language Processing in Python
DataCamp
DECEMBER 2020 - PRESENT
Natural Language Processing Specialization
DeepLearning.AI | via Coursera
OCTOBER 2020 - PRESENT
AI in Healthcare Specialization
Stanford University | via Coursera
OCTOBER 2018 - PRESENT
Deep Learning Specialization
DeepLearning.AI | via Coursera
Skills
Libraries/APIs
Spark NLP, TensorFlow, PySpark, Spark ML
Tools
Microsoft Excel, SOLIDWORKS
Languages
Python, Python 3
Industry Expertise
Bioinformatics, Healthcare
Storage
JSON
Platforms
Amazon Web Services (AWS), AWS IoT
Other
Natural Language Processing (NLP), Machine Learning, Data Visualization, Biochemistry, Analytics, Biology, Pharmacology, R&D, Engineering, CSV File Processing, Excel Expert, Interactive Charts, Chatbots, Patents, Generative Pre-trained Transformers (GPT), Biomedical Skills, Language Models, Unstructured Data Analysis, Artificial Intelligence (AI), Biomaterial, Composite Materials, Data Science, Deep Learning, Dash, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Sequence Models, Entrepreneurship, Web Scraping, Time Series Analysis, Computational Biology, Game AI, Emotion Recognition, Chatbot Conversation Design, LangChain, Weaviate, Pinecone, Cell Biology, Materials Science, 3D Printing, Product Development, Model Deployment, Generative Adversarial Networks (GANs), Single-cell Modeling, CTO, Pitch Preparation, Medical Diagnostics, OpenAI, Generative Pre-trained Transformer 3 (GPT-3), Google Custom Search, Generative Artificial Intelligence (GenAI), Healthcare IT
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