ProfilePilot
An Android app with 500+ downloads that coaches people to a stronger professional profile, without inventing a single achievement.
Android, Supabase Edge Functions, Deno, Postgres, Groq, gpt-oss-120b
Open to AI/ML roles
AI/ML engineer in Mumbai. Computer engineering graduate, 2026. Building in public.
An Android app with 500+ downloads that coaches people to a stronger professional profile, without inventing a single achievement.
Android, Supabase Edge Functions, Deno, Postgres, Groq, gpt-oss-120b
A Chrome extension that reads a tough negotiation email in Gmail and drafts three fact-checked replies you can insert in one click.
Chrome Extension (MV3), React, Vite, Tailwind CSS, Node.js, Express, Zod, Groq, gpt-oss-120b, Supabase, Razorpay, Render
This site: a portfolio built as an AI system, with an agent that answers from my own content and the testing and monitoring around it in public.
Next.js, TypeScript, Groq, Gemini, BM25, Embeddings, Upstash Redis, MediaPipe, WebLLM, Vercel, GitHub Actions
A ChatGPT-style assistant running on my own server, set up with AI help.
Qwen2.5, Ollama, OpenWebUI, Nginx, DigitalOcean
Paste a headline or article and get a real-or-fake verdict in seconds.
Python, scikit-learn, TF-IDF, NLTK, Flask, Supabase, Google OAuth
Turns raw transactions into customer segments a business can act on, served to a web app and an Android app from one API.
Python, scikit-learn, K-Means, FastAPI, AWS EC2, Streamlit, Kotlin
Estimates how likely a loan applicant is to default, tuned to catch more risky applicants rather than to look accurate.
Save the links you want to keep, sort them into categories and find them again with search.
Ask questions about a PDF and get answers with the page numbers they came from.
Predicts a student's final exam marks from 18 academic, study and lifestyle factors.

I'm Sangam, an AI/ML engineer from Mumbai. I graduated in computer engineering from CSMIT, Mumbai University in 2026, and completed a professional certification in data science and AI at IT Vedant.
My own hands-on work is data science and classic machine learning in Python: I clean and explore data with pandas, train and evaluate models with scikit-learn, and serve them with FastAPI and Streamlit, as in Customer Intelligence (on AWS), Credit Risk and NewsIntel's classifier.
I also ship AI products using AI coding assistants. For ProfilePilot (500+ downloads on Google Play), DealShield AI (Chrome Web Store), Quanta and this site, the idea and the launch are mine and the assistant wrote the code. My part is the product: I write what to build, test every feature, feed errors back until they are fixed, steer the assistant when it goes the wrong way, and handle keys, deployment and the store listings. I'm now learning prompt engineering, RAG, LLM APIs and deep learning so I can build that layer myself.
Outside product work I study markets. Quantitative finance and algorithmic trading are where my ML and my curiosity meet.
Worked with me? Write a recommendation
Estimates how likely a loan applicant is to default, tuned to catch more risky applicants rather than to look accurate.
Python, scikit-learn, HistGradientBoosting, updated 11 November 2026
A Chrome extension that reads a tough negotiation email in Gmail and drafts three fact-checked replies you can insert in one click.
Chrome Extension (MV3), React, Vite, updated 10 November 2026
Paste a headline or article and get a real-or-fake verdict in seconds.
Python, scikit-learn, TF-IDF, updated 17 October 2026
Turns raw transactions into customer segments a business can act on, served to a web app and an Android app from one API.
Python, scikit-learn, K-Means, updated 8 October 2026
Ask questions about a PDF and get answers with the page numbers they came from.
Python, LangChain, FAISS, updated 1 September 2026
Estimates a California district's median house value; the best of nine models I compared explains 83% of the variance.
Python, scikit-learn, pandas, updated 1 September 2026
Training, evaluating and serving ML models (Customer Intelligence, Credit Risk, NewsIntel), and shipping AI products with AI coding assistants: ProfilePilot (500+ downloads on Google Play) and DealShield AI (Chrome Web Store).
Real-world ML projects in business insight, predictive modelling and data storytelling.
Financial data modelling and statistical research on market data.
Predictive modelling of customer behaviour and an end-to-end ML pipeline.
Data cleaning, visualisation and business insight for client deliverables.
Power BI dashboards and business reporting.
Customer analytics and statistical analysis for the grocery sector.
CSMIT, University of Mumbai, June 2022 to May 2026
Final-year project: NewsIntel, an NLP-based fake news detection system.
IT Vedant, December 2025 to 2026
Coursework: machine learning, deep learning, NLP, Power BI, SQL and Python for data analytics.
IBM, via IT Vedant
IBM, via IT Vedant
IBM, via IT Vedant
IT Vedant
Udemy, 2025
Asmita Patel Global School of Trading, 2024
Open to AI/ML engineer, ML engineer and data scientist roles: full-time, contract or remote.