Muhammad is available for hire
Hire MuhammadMuhammad Shahid Sharif
Verified Expert in Engineering
SQL Developer
Lahore, Punjab, Pakistan
Toptal member since June 18, 2025
Bio
Shahid, a skilled data analyst and scientist with over five years of experience, excels at transforming raw data into actionable business insights. His expertise spans enhancing attribution accuracy at Coursera to crafting impactful dashboards in Looker, combining technical acumen with strategic foresight. Shahid is your go-to for data that powers decision-making. Additionally, he has authored two Python packages published on PyPI.
Portfolio
Precision Drilling
Artificial Intelligence (AI), Machine Learning...
SCPM Media LLC
Large Language Models (LLMs), Replit, React, Node.js, MySQL...
INEFFABLE PICTURES LLC
Artificial Intelligence (AI), Web Scraping, SQL, Node.js, React, ETL...
Experience
- SQL - 7 years
- Python - 6 years
- Python 3 - 6 years
- GitHub - 5 years
- Data Visualization - 5 years
- Machine Learning - 4 years
- Natural Language Processing (NLP) - 3 years
- Looker - 3 years
Preferred Environment
Python 3, SQL, MySQL, Databricks, Looker, Jira, GitHub, PyTorch, Keras, Pandas
The most amazing...
...moment in my career was leading the rebuild of Coursera’s attribution pipeline—boosting accuracy by 22% and shaping key business decisions.
Work Experience
AI/ML Developer
2026 - PRESENT
Precision Drilling
- Developed a high-performance data extraction pipeline utilizing OCR and NLP to process complex PDF documents, achieving a 95% accuracy rate in structured data recovery from unstructured sources.
- Refined chatbot dialogue flows and prompt engineering strategies, which decreased average response latency by 2 seconds and significantly improved user satisfaction scores (CSAT).
- Optimized an AI-driven conversational bot by implementing advanced retrieval-augmented generation (RAG) techniques, resulting in a 30% increase in intent recognition accuracy and response relevance.
- Automated the ingestion and transformation of large-scale document sets into a vector database, reducing manual data entry time by approximately 40 hours per week.
Technologies: Artificial Intelligence (AI), Machine Learning, Generative Artificial Intelligence (GenAI), PyTorch, LangChain, Scikit-learn, Azure, Azure OpenAI Service, Keras, Vibe Coding, AI Agents, Agentic AI, Cursor AI, Azure SQL, Snowflake, Claude, Claude API
Consultant
2025 - 2026
SCPM Media LLC
- Engineered a scalable SaaS architecture. Led the transition from a Replit prototype to a production-ready environment, architecting a high-performance React front end and a robust Python back end to ensure system reliability and future scalability.
- Optimized AI strategy and integration. Architected a custom LLM integration layer using Python to connect proprietary marketing logic with OpenAI APIs, automating the generation of high-converting ad copy and sophisticated creative prompts.
- Architected data-driven marketing logic. Designed and implemented a PostgreSQL database schema to manage complex campaign data, user configurations, and multi-tier audience segmentation, ensuring data integrity across the MVP.
- Delivered automated campaign solutions. Developed the core engine that translates user inputs into a comprehensive "Campaign Recommendation Package," featuring budget utilization models and exportable PDF reports for Meta Ads.
- Worked as a technical lead and consultant. Acted as the primary technical advisor to translate the founder’s 9-year marketing framework into a functional software roadmap, balancing rapid MVP deployment with sound architectural principles.
Technologies: Large Language Models (LLMs), Replit, React, Node.js, MySQL, Full-stack Development, Amazon Web Services (AWS), Midjourney, AI Engineering, Enterprise AI, Agentic AI, Claude, Claude API, Workflows
Automation/AI Consultant | Full-stack Developer
2025 - 2026
INEFFABLE PICTURES LLC
- Automated large-scale data collection workflows using Selenium-based scrapers with proxy rotation, residential IP pools, and anti-blocking strategies, reducing manual claim lookup work by over 85%.
- Built end-to-end ETL pipelines that extracted, cleaned, validated, and centralized data from multiple websites, emails, and APIs into a unified PostgreSQL-backed system.
- Designed and deployed a single-source-of-truth dashboard using React and Node.js that integrated scraped data, AI-generated summaries, and operational metrics into one clean, actionable page.
Technologies: Artificial Intelligence (AI), Web Scraping, SQL, Node.js, React, ETL, Automation, Full-stack Development, Azure, Amazon Web Services (AWS), Databases, Zapier, n8n, OpenAI, LangChain, Python, Machine Learning, Communication, Multimodal Models, Data Scientist, Excel 365, Image Generation, Text to Image, Web Development, API Integration, Analytics, Back-end Development, Clean Code, Documentation, Role-based Access Control (RBAC), Logging, Stripe, Stripe API, Business Rules Engine, Website Data Scraping, Prompt Engineering, Data Preprocessing, Information Extraction, CSV, Slack, Cron, Looker Studio, Analysis, AI Engineering, Enterprise AI, Agentic AI, Claude, Claude API, Workflows
Google Sheets Expert
2025 - 2025
BRIAN AND SONS,INC
- Cleaned and transformed messy datasets, unlocking clear, accurate visualizations that revealed key business trends.
- Automated the employee-data onboarding process into a single-click workflow, reducing manual effort and ensuring real-time accuracy.
- Designed and built interactive dashboards in Google Sheets, turning raw data into actionable insights for faster decision-making.
Technologies: JavaScript, CSS, HTML, AngularJS, Amazon Web Services (AWS), MySQL, Google Sheets, API Integration, Analytics, Clean Code, Data Preprocessing, Information Extraction, Analysis, Workflows
AI Developer/Consultant
2025 - 2025
Afton Energy LLC
- Automated manual sales processes by leveraging AI to streamline lead email generation and meeting scheduling, improving overall efficiency without the need for a formal CRM system.
- Analyzed and optimized business workflows using AI-driven solutions, identifying key areas for process improvement across multiple sales and operational tasks.
- Implemented AI solutions in collaboration with clients, enhancing sales productivity and driving measurable improvements in business process efficiency.
Technologies: Artificial Intelligence (AI), Automation, Data Modeling, Communication, Data Scientist, Excel 365, Image Generation, Text to Image, API Integration, Back-end Development, Clean Code, Role-based Access Control (RBAC), Logging, Business Rules Engine, Website Data Scraping, Prompt Engineering, Data Preprocessing, Information Extraction, CSV, Slack, Cron, Looker Studio, Analysis, AI Engineering, Enterprise AI, Agentic AI, Claude, Claude API
Data Scientist and Analyst
2025 - 2025
Bilal Ahmad
- Built an automated NLP pipeline that extracted thousands of customer reviews across multiple platforms, applied sentiment and theme clustering, and produced weekly insight reports used by product teams to guide feature updates.
- Designed GPT-powered summarization workflows that converted long-form user feedback into clean, actionable insights with over 90% reduction in manual review time.
- Streamlined end-to-end workflow from raw text extraction to GPT-based reporting, reducing turnaround time for weekly insights by 60%.
- Developed a scalable data extraction system using web scraping and API-based ingestion to continuously pull fresh Amazon-style product reviews and store them for analysis.
Technologies: Project Management, ChatGPT, ChatGPT API, Data Analysis, Natural Language Processing (NLP), Agile, Data Engineering, Data Modeling, Pivot Tables, Communication, Data Scientist, Image Generation, Text to Image, API Integration, CRM Systems, Analytics, Data Validation, Key Performance Indicators (KPIs), Back-end Development, Clean Code, Role-based Access Control (RBAC), Logging, Business Rules Engine, Prompt Engineering, Data Preprocessing, CSV, Slack, Looker Studio, Analysis, Enterprise AI
Full-stack Developer
2025 - 2025
Murad Younis Healthcare Inc.
- Developed an AI-based web app that extracts and normalizes handwritten or printed medical prescriptions using OCR and NLP pipelines.
- Designed logic to expand medical abbreviations and standardize drug instructions for better clarity and accuracy.
- Deployed the end-to-end system on Render, improving prescription readability and reducing manual processing time.
Technologies: MySQL, Databases, Back-end, Data Extraction, Business Logic, Python, AI Tools, Document Processing, Data Profiling, Microsoft Outlook, Recommendation Systems, Generative Artificial Intelligence (GenAI), Image Analysis, OpenAI, FastAPI, Data Modeling, Pivot Tables, Communication, Multimodal Models, Optical Character Recognition (OCR), Data Scientist, Image Generation, Web Development, CRM Systems, Analytics, Back-end Development, Clean Code, Role-based Access Control (RBAC), Logging, Business Rules Engine, Website Data Scraping, Prompt Engineering, Data Preprocessing, Information Extraction, CSV, Slack, Looker Studio, Analysis, AI Engineering, Enterprise AI, Claude, Claude API
Google Sheets Expert
2025 - 2025
Brian and Sons, Inc.
- Cleaned and transformed messy datasets, unlocking clear, accurate visualizations that revealed key business trends.
- Automated the employee-data onboarding process into a single-click workflow, reducing manual effort and ensuring real-time accuracy.
- Designed and built interactive dashboards in Google Sheets, turning raw data into actionable insights for faster decision-making.
Technologies: Google Sheets, Data Engineering, Excel 2016, Excel VBA, Data Cleaning, Data Scraping, Coding, Git, Back-end, Business Logic, Data Extraction, Databases, AI Design, APIs, AI Adoption, AI Chatbots, AI Compliance Agents, Full-stack Development, Large Language Models (LLMs), PostgreSQL, REST APIs, Dashboard Development, ChatGPT API, Google Forms, AI Tools, Business Intelligence (BI), Microsoft Outlook, Recommendation Systems, OpenAI, FastAPI, Data Modeling, Pivot Tables, Communication, Data Scientist, Excel 365, CRM Systems, Analytics, Data Validation, Clean Code, Data Preprocessing, Information Extraction, Slack, Looker Studio, Analysis
Data Analyst
2025 - 2025
Noosphere Inc
- Analyzed customer behavior data for churn prediction and retention.
- Gathered data from multiple sources like Amplitude, iOS App Store, RevenueCat, and social media accounts for analysis.
- Shared key feedback with the CEO to make appropriate product changes to lower churn rate and improve retention.
Technologies: Data Analysis, Data Engineering, Data Science, Tableau, Excel 2016, Coding, Git, Back-end, Business Logic, Data Extraction, Databases, AI Design, AI Programming, APIs, AI Adoption, AI Agents, AI Art Generator, AI Automation, AI Chatbots, AI Compliance Agents, Full-stack Development, Large Language Models (LLMs), PostgreSQL, REST APIs, Dashboard Development, Project Management, ChatGPT, ChatGPT API, Conversational AI, Full-stack, AI Tools, Business Intelligence (BI), Dashboard Design, Data Profiling, Data Classification, Data Processing, AI Data Classification, Microsoft Outlook, Recommendation Systems, Statistics, Statistical Modeling, Demand Forecasting, Generative Artificial Intelligence (GenAI), Predictive Analytics, Algorithms, OpenAI, FastAPI, Data Modeling, Pivot Tables, LTV:CAC, Lifetime Value (LTV), Marketing Analytics, Marketing Attribution, Communication, Data Labeling, Data Pipelines, Data Scientist, CRM Systems, Analytics, BI Reporting, Data Validation, Key Performance Indicators (KPIs), Back-end Development, Clean Code, Documentation, Role-based Access Control (RBAC), Logging, Website Data Scraping, Data Preprocessing, CSV, Slack, Looker Studio, Analysis, AI Engineering, Enterprise AI, Claude API, Workflows
Data Scientist and Analyst
2022 - 2025
Coursera
- Improved Coursera’s enrollment attribution accuracy from 56% to 78%, enhancing campaign targeting and boosting marketing ROI.
- Developed high-impact Looker dashboards used by executives to monitor weekly revenue trends, funnel performance, and attribution quality.
- Migrated multiple analytics pipelines from Amazon Redshift (EDW) to Databricks (EDS), reducing query latency by 40% and improving data reliability.
- Built automated ETL workflows for Degree DS tables and attribution models, ensuring consistent and accurate reporting across teams.
- Uncovered key data quality issues in enrollment funnels through anomaly detection, leading to improved upstream processes with partner institutions.
- Documented over 20 degree KPIs and metric definitions, standardizing reporting across product, growth, and data teams.
- Led internal workshops on Looker development and data app design, accelerating adoption of self-service analytics practices across the organization.
- Delivered over 50 ad-hoc analyses to support cross-functional stakeholders, enabling data-backed decisions for program launches and user engagement strategies.
- Onboarded new analysts and product managers by creating domain-specific documentation and leading structured training sessions.
- Audited attribution pipelines and enrollment data flow to proactively detect inconsistencies, improving data trust and reporting accuracy.
Technologies: Python, SQL, Apache Airflow, Databricks, Looker Modeling Language (LookML), Looker, Google Sheets, Data Visualization, Dashboards, Finance, Forecasting, Time Series Forecasting, Automation, Airtable, Reporting, Code Review, Debugging, Testing, English, Data Reporting, Microsoft Excel, Data Science, Tableau, Coding, Git, Back-end, Business Logic, Data Extraction, Databases, AI Design, AI Programming, APIs, AI Adoption, AI Agents, AI Algorithms, AI Art Generator, AI Automation, AI Chatbots, AI Compliance Agents, Full-stack Development, Large Language Models (LLMs), Amazon Web Services (AWS), Matching Systems, PostgreSQL, Dashboard Development, Project Management, ChatGPT, ChatGPT API, Conversational AI, AI Tools, Retrieval-augmented Generation (RAG), Document Processing, Business Intelligence (BI), Dashboard Design, Data Profiling, Data Classification, Data Processing, AI Data Classification, Microsoft Outlook, Microsoft Power Automate, Recommendation Systems, Statistics, Statistical Modeling, Demand Forecasting, Generative Artificial Intelligence (GenAI), Predictive Analytics, Algorithms, Image Analysis, FastAPI, Reinforcement Learning, Time Series Analysis, Data Modeling, Pivot Tables, A/B Testing, LTV:CAC, Lifetime Value (LTV), Marketing Analytics, Marketing Attribution, Communication, Snowflake, Computer Vision, Data Labeling, Data Pipelines, Multimodal Models, Optical Character Recognition (OCR), Data Scientist, TensorFlow, CRM Systems, Analytics, BI Reporting, Data Validation, Key Performance Indicators (KPIs), Back-end Development, Clean Code, Documentation, Logging, Data Preprocessing, CSV, Slack, Looker Studio, Analysis, AI Engineering, Enterprise AI, Workflows
Senior AI Engineer and Data Analyst
2022 - 2023
Ascend Healthcare Solutinos
- Developed domain-specific AI assistants and voice-assisted personal assistants to provide an immersive experience.
- Implemented robotic process automation to streamline complex processes, reducing resource requirements and saving 20 hours per week in manual work.
- Automated data processing and data analysis by building robust data pipelines.
- Built and maintained Power BI dashboards to monitor the performance of healthcare data.
Technologies: Python, SQL, Microsoft Power BI, Power BI Desktop, Rasa NLU, Natural Language Processing (NLP), Machine Learning, Chatbots, Data Science, Tableau, Data Scraping, Coding, Git, Back-end, Business Logic, Data Extraction, Databases, AI Design, AI Programming, APIs, Full-stack Development, PostgreSQL, REST APIs, Dashboard Development, Project Management, Conversational AI, Business Intelligence (BI), Dashboard Design, Data Profiling, Data Processing, Microsoft Outlook, Microsoft Power Automate, Recommendation Systems, Statistics, Statistical Modeling, Predictive Analytics, Algorithms, FastAPI, Reinforcement Learning, Time Series Analysis, Data Modeling, Pivot Tables, Communication, Data Scientist, TensorFlow, Analytics, BI Reporting, Data Validation, Key Performance Indicators (KPIs), Back-end Development, Clean Code, Documentation, Logging, Data Preprocessing, CSV, Slack, Analysis, AI Engineering
Data Scientist
2019 - 2022
FiveRivers Technologies
- Developed AI-Studio, a drag-and-drop low-code/no-code platform that enabled non-technical users to build AI workflows and solve business challenges efficiently.
- Designed modular machine learning components for AI Studio, allowing users to assemble custom models without writing code.
- Streamlined model deployment processes, reducing time-to-production for custom ML workflows by 60%.
- Built reusable templates and pipelines for predictive analytics, classification, and NLP use cases within the platform.
- Reduced onboarding friction for business analysts and citizen data scientists by enabling code-free experimentation and deployment.
- Led multiple client demos and technical workshops to demonstrate AI-Studio’s capabilities and gather iterative product feedback.
- Improved user engagement metrics for the AI-Studio platform through continuous optimization based on user behavior analytics.
Technologies: Python 3, Machine Learning, Natural Language Processing (NLP), Neural Networks, Pandas, NumPy, SpaCy, Finance, Forecasting, Time Series Forecasting, Stock Trading, JavaScript, Artificial Intelligence (AI), Web Applications, Automation, Reporting, Code Review, Debugging, Testing, English, Data Reporting, Microsoft Excel, Data Science, Tableau, Data Scraping, Coding, Git, Back-end, AI Design, APIs, Voice Cloning, Full-stack Development, PostgreSQL, REST APIs, Dashboard Development, Project Management, Conversational AI, Document Processing, Business Intelligence (BI), Dashboard Design, Data Profiling, Data Processing, Microsoft Outlook, Microsoft Power Automate, Statistical Modeling, Predictive Analytics, Algorithms, Monte Carlo Analysis, Monte Carlo Simulations, FastAPI, Reinforcement Learning, Time Series Analysis, Data Modeling, Pivot Tables, Communication, Computer Vision, Data Scientist, TensorFlow, Analytics, BI Reporting, Data Validation, Key Performance Indicators (KPIs), Back-end Development, Logging, Data Preprocessing, CSV, Slack, Analysis
Experience
Real-time Rehearsal Conversational Agent
https://script-actor-ai-1.onrender.com/A real-time conversational AI tool that lets actors rehearse scripts with lifelike AI co-actors. It automatically detects characters from uploaded scripts, assigns gender- and age-appropriate voices using ElevenLabs, and enables natural back-and-forth dialogue powered by ChatGPT. Built with Node.js, React, and AWS, it delivers seamless, scalable, and human-like rehearsal experiences for the film industry.
SkinCare AI
https://skin-sage-buddy.onrender.comAn intelligent skincare recommendation system that analyzes individual skin profiles to suggest ingredients and products based on scientific dermatological evidence.
How It Works
• Data Collection: Users fill out a skin assessment or upload facial images.
Image Analysis: Computer vision (TensorFlow and OpenCV) detects issues such as dryness, acne, or pigmentation.
• NLP Understanding: GPT-4 and domain-tuned NLP models interpret user concerns and preferences.
• Knowledge Base: Integrates evidence-based dermatological research for ingredient validation.
• Recommendation Engine: A hybrid of content-based and rule-based algorithms suggests ingredients (e.g., niacinamide and retinol) and matching products ranked by efficacy and compatibility.
• Continuous Learning: Reinforcement learning refines recommendations using user feedback.
Tech Stack
React, Tailwind, FastAPI, PostgreSQL, GPT-4, TensorFlow, OpenCV.
Results
Achieved 85% recommendation accuracy, reducing skincare research time by 70%, and delivering personalized, science-backed skincare intelligence.
How It Works
• Data Collection: Users fill out a skin assessment or upload facial images.
Image Analysis: Computer vision (TensorFlow and OpenCV) detects issues such as dryness, acne, or pigmentation.
• NLP Understanding: GPT-4 and domain-tuned NLP models interpret user concerns and preferences.
• Knowledge Base: Integrates evidence-based dermatological research for ingredient validation.
• Recommendation Engine: A hybrid of content-based and rule-based algorithms suggests ingredients (e.g., niacinamide and retinol) and matching products ranked by efficacy and compatibility.
• Continuous Learning: Reinforcement learning refines recommendations using user feedback.
Tech Stack
React, Tailwind, FastAPI, PostgreSQL, GPT-4, TensorFlow, OpenCV.
Results
Achieved 85% recommendation accuracy, reducing skincare research time by 70%, and delivering personalized, science-backed skincare intelligence.
RevvIQ
https://mshahidsharif.com/portfolio/revviqBusiness Problem
Legal and claims teams need actionable intelligence from fragmented public sources — NY Workers' Compensation claims (NYOSC), Westlaw research, and New York eCourts dockets — but each portal is siloed, hard to monitor at scale, and impossible to join without heavy manual work. Clients also need keyword-driven discovery and a way to query the resulting warehouse in plain English.
Solution
Built RevvIQ as an end-to-end data platform: scrapers for NYOSC claim search, Thomson Reuters Westlaw, and NY eCourts; Python pipelines for preprocessing, wrangling, extraction, and analysis; address-based record matching and client-keyword scrape orchestration; a React front end with Resend for transactional email; and an AI conversational agent that generates SQL from user questions and returns live results. Deployed on Render.
Unifies multiportal legal and claims data into a queryable, matched dataset — so teams can monitor keywords, link records by address, and ask natural-language questions against the warehouse instead of stitching portals by hand.
Legal and claims teams need actionable intelligence from fragmented public sources — NY Workers' Compensation claims (NYOSC), Westlaw research, and New York eCourts dockets — but each portal is siloed, hard to monitor at scale, and impossible to join without heavy manual work. Clients also need keyword-driven discovery and a way to query the resulting warehouse in plain English.
Solution
Built RevvIQ as an end-to-end data platform: scrapers for NYOSC claim search, Thomson Reuters Westlaw, and NY eCourts; Python pipelines for preprocessing, wrangling, extraction, and analysis; address-based record matching and client-keyword scrape orchestration; a React front end with Resend for transactional email; and an AI conversational agent that generates SQL from user questions and returns live results. Deployed on Render.
Unifies multiportal legal and claims data into a queryable, matched dataset — so teams can monitor keywords, link records by address, and ask natural-language questions against the warehouse instead of stitching portals by hand.
AI-powered Prescription Analyzer for Medication Validation and Insights
An intelligent healthcare application that analyzes medical prescriptions to extract, validate, and structure drug-related information using NLP and OCR technologies.
How It Works
• Document Processing: Uses OCR (Tesseract and EasyOCR) to extract handwritten or printed text from prescription images.
• Entity Recognition: NLP models (spaCy, GPT-4) identify key medical entities—drug names, dosages, frequencies, and routes.
• Validation Engine: Cross-references extracted data with a drug knowledge base (RxNorm and FDA APIs) to flag interactions or inconsistencies.
• Structured Output: Converts unstructured prescription data into a clean JSON format, ready for integration with EHR or pharmacy systems.
• Insights Dashboard: Provides visual summaries of prescribed drugs, potential side effects, and dosage trends for pharmacists or clinicians.
Tech Stack
Python, FastAPI, PostgreSQL, GPT-4, spaCy, Tesseract OCR, Streamlit.
Results
Improved prescription processing accuracy by 92%, reduced manual review time by 60%, and enhanced patient safety through automated validation.
How It Works
• Document Processing: Uses OCR (Tesseract and EasyOCR) to extract handwritten or printed text from prescription images.
• Entity Recognition: NLP models (spaCy, GPT-4) identify key medical entities—drug names, dosages, frequencies, and routes.
• Validation Engine: Cross-references extracted data with a drug knowledge base (RxNorm and FDA APIs) to flag interactions or inconsistencies.
• Structured Output: Converts unstructured prescription data into a clean JSON format, ready for integration with EHR or pharmacy systems.
• Insights Dashboard: Provides visual summaries of prescribed drugs, potential side effects, and dosage trends for pharmacists or clinicians.
Tech Stack
Python, FastAPI, PostgreSQL, GPT-4, spaCy, Tesseract OCR, Streamlit.
Results
Improved prescription processing accuracy by 92%, reduced manual review time by 60%, and enhanced patient safety through automated validation.
Degrees KPI Dashboard
Degrees KPI Dashboard | Coursera
Looker | SQL | Data Modeling | Stakeholder Reporting
I led the design and development of a comprehensive Degrees KPI Dashboard that unified funnel activity, revenue data, and enrollment metrics into a single, intuitive interface. The dashboard enabled stakeholders to track business performance over time through interactive time-series visualizations and key performance indicators.
I integrated multiple data sources using LookML to ensure accurate, real-time reporting and built modular views to support deep-dive analysis for marketing, finance, and program teams. The dashboard significantly improved decision-making efficiency by surfacing trends and anomalies quickly, and became a core part of weekly business reviews.
Looker | SQL | Data Modeling | Stakeholder Reporting
I led the design and development of a comprehensive Degrees KPI Dashboard that unified funnel activity, revenue data, and enrollment metrics into a single, intuitive interface. The dashboard enabled stakeholders to track business performance over time through interactive time-series visualizations and key performance indicators.
I integrated multiple data sources using LookML to ensure accurate, real-time reporting and built modular views to support deep-dive analysis for marketing, finance, and program teams. The dashboard significantly improved decision-making efficiency by surfacing trends and anomalies quickly, and became a core part of weekly business reviews.
SimpleEDA
https://github.com/shahid017/SimpleEDASimpleEDA is a lightweight Python package I built to automate and simplify the EDA process for data analysts and scientists. With just a few lines of code, it delivers comprehensive data summaries, visualizations, and outlier detection—all without repetitive boilerplate. From correlation analysis to feature selection, SimpleEDA accelerates data understanding, making it ideal for fast prototyping and reporting. Whether profiling data for a machine learning model or exploring patterns in a new dataset, SimpleEDA brings structure, speed, and clarity to your workflow.
Degrees Attribution Model
As part of Coursera’s data team, I led the development of a new attribution model that significantly improved the tracking of user enrollments back to marketing sources. The original attribution accuracy was 56%, limiting the company’s ability to evaluate campaign effectiveness. I redesigned the attribution pipeline, implemented SQL and Looker enhancements, and optimized key data flows in Databricks.
NlpHub
https://github.com/shahid017/NlpHubNlpHub is a sleek Python library I crafted to simplify Natural Language Processing (NLP) by wrapping powerful tools like spaCy and NLTK into a clean, user-friendly API. With just a few lines of code, NlpHub lets you perform core NLP tasks—such as annotation, transformation, sentiment analysis, and text-to-speech—streamlining workflows and removing friction. Whether you're prototyping language models, automating annotation pipelines, or generating audio from text, NlpHub speeds up development and keeps your codebase lean.
KiniScore
KiniScore‑Backend – Unified Soccer Data Scraper
KiniScore‑Backend is a custom-built Python scraper I developed to aggregate rich soccer player and match statistics from three distinct online sources into a single normalized back end. With a modular, resilient design, it handles diverse HTML structures, API responses, and rate limits. Then it cleans, deduplicates, and merges the data into a unified dataset with over 40 metrics per player (both men’s and women’s). Tailored for sports analysts and developers, it delivers high-quality, ready-to-use data for visualizations, predictive models, and performance insights.
KEY HIGHLIGHTS
• Multi-source fusion: Collects and harmonizes data from three independent soccer platforms.
• Robust pipelines: Custom parsers, deduplication, and error handling ensure accuracy.
• Scalable and modular: Easily extensible for new data sources or metrics.
KiniScore‑Backend is a custom-built Python scraper I developed to aggregate rich soccer player and match statistics from three distinct online sources into a single normalized back end. With a modular, resilient design, it handles diverse HTML structures, API responses, and rate limits. Then it cleans, deduplicates, and merges the data into a unified dataset with over 40 metrics per player (both men’s and women’s). Tailored for sports analysts and developers, it delivers high-quality, ready-to-use data for visualizations, predictive models, and performance insights.
KEY HIGHLIGHTS
• Multi-source fusion: Collects and harmonizes data from three independent soccer platforms.
• Robust pipelines: Custom parsers, deduplication, and error handling ensure accuracy.
• Scalable and modular: Easily extensible for new data sources or metrics.
Education
2017 - 2019
Master's Degree in Computer Science
National University of Computer and Emerging Sciences, FAST - Islamabad, Pakistan
2012 - 2016
Bachelor's Degree in Computer Science
COMSATS University Islamabad - Sahiwal, Pakistan
Certifications
JULY 2025 - PRESENT
What Is Generative AI?
JANUARY 2024 - PRESENT
Analyzing and Visualizing Data in Looker
Coursera
NOVEMBER 2019 - PRESENT
Neural Networks and Deep Learning
Coursera
JUNE 2019 - PRESENT
Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
Coursera
Skills
Libraries/APIs
REST APIs, Claude API, Pandas, NumPy, SpaCy, Beautiful Soup, Requests, Natural Language Toolkit (NLTK), TensorFlow, Stripe, Stripe API, PyTorch, Keras, Rasa NLU, React, Node.js, Scikit-learn
Tools
GitHub, Slack, Git, Logging, Claude, Looker, Jira, Apache Airflow, Google Sheets, PyPI, ChatGPT, Cron, Microsoft Excel, Tableau, Excel 2016, Google Forms, Microsoft Outlook, Microsoft Power BI, Power BI Desktop, Zapier, n8n, Azure OpenAI Service
Languages
Python 3, SQL, Python, Looker Modeling Language (LookML), JavaScript, PHP, HTML, CSS, Java, Excel VBA, Snowflake
Paradigms
Business Intelligence (BI), Clean Code, Role-based Access Control (RBAC), Automation, Testing, Agile, ETL
Storage
MySQL, Databases, PostgreSQL, Data Pipelines, Data Validation, Azure SQL
Industry Expertise
Project Management, AI Art Generator
Frameworks
Business Rules Engine, Tailwind CSS, AngularJS
Platforms
Amazon Web Services (AWS), Microsoft Power Automate, Databricks, Azure, Replit
Other
Machine Learning, Data Visualization, Dashboards, Data Analysis, Data Analytics, Exploratory Data Analysis, Data Preprocessing, CSV, Looker Studio, Analysis, Forecasting, Reporting, Code Review, Debugging, English, Data Reporting, Data Science, Coding, Back-end, Business Logic, Data Extraction, APIs, Full-stack Development, Large Language Models (LLMs), Document Parsing, Dashboard Development, Dashboard Design, Data Profiling, FastAPI, Data Modeling, Pivot Tables, LTV:CAC, Communication, Data Labeling, Data Scientist, Excel 365, Text to Image, Web Development, API Integration, Analytics, BI Reporting, Key Performance Indicators (KPIs), Back-end Development, Documentation, AI Engineering, Workflows, Natural Language Processing (NLP), Deep Learning, Neural Networks, Scraping, Web Scraping, Data Collection, Data Cleaning, Database Normalization, Prompt Engineering, Information Extraction, Data Engineering, Finance, Time Series Forecasting, Stock Trading, Artificial Intelligence (AI), Web Applications, Airtable, Data Scraping, Minimum Viable Product (MVP), AI Design, AI Programming, AI Adoption, AI Agents, AI Algorithms, AI Automation, AI Chatbots, AI Compliance Agents, Voice Cloning, Matching Systems, ChatGPT API, Conversational AI, Full-stack, AI Tools, Retrieval-augmented Generation (RAG), Document Processing, Data Classification, Data Processing, AI Data Classification, Recommendation Systems, Statistics, Statistical Modeling, Demand Forecasting, Generative Artificial Intelligence (GenAI), Predictive Analytics, Algorithms, Monte Carlo Analysis, Monte Carlo Simulations, Image Analysis, OpenAI, Website Data Scraping, Reinforcement Learning, Time Series Analysis, A/B Testing, Lifetime Value (LTV), Marketing Analytics, Marketing Attribution, Computer Vision, Multimodal Models, Optical Character Recognition (OCR), Image Generation, CRM Systems, Enterprise AI, Agentic AI, Amazon Redshift, Stakeholder Engagement, Chatbots, Cursor AI, LangChain, Midjourney, Vibe Coding
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