Sangam Gupta

+91 9970116435, contact@sangamgupta.in, Mumbai, India

linkedin.com/in/thesangamx, github.com/TheSangamX, sangamgupta.in

Summary

AI/ML engineer who builds and ships machine-learning and LLM products end to end: ProfilePilot, an AI profile coach with 500+ downloads on Google Play; a self-hosted LLM assistant; and a customer segmentation model served from AWS to web and Android. Computer engineering graduate (2026).

Skills

Languages and data:

Python, SQL, NumPy, pandas, Statistics, MySQL, Supabase

Machine learning:

scikit-learn, EDA, Feature engineering, Model evaluation, K-Means, PCA, RFM analysis, NLP, NLTK, LLMs, RAG, Deep learning

Products and APIs:

FastAPI, Pydantic, Uvicorn, Flask, Streamlit, REST APIs

Infrastructure and LLM tooling:

AWS EC2, DigitalOcean, Nginx, Linux, Ollama, OpenWebUI, LangChain, FAISS, Git

Analytics:

Power BI, Excel, Tableau, Matplotlib, Seaborn, Jupyter

Projects

• ProfilePilotLiveCase study

  Android, Supabase Edge Functions, Deno, Postgres, Groq, gpt-oss-120b

  AI profile coach on Google Play: profile score and audit, headlines, About, experience bullets, job match, messages, interview prep and posts. Eight tools behind one Supabase Edge Function calling Groq's gpt-oss-120b with strict JSON schemas.

  500+ downloads on Google Play; 8 AI tools with strict JSON-schema outputs; per-device and per-IP daily quotas enforced in Postgres.

• Customer IntelligenceLiveCase study

  Python, scikit-learn, K-Means, FastAPI, AWS EC2, Streamlit, Kotlin

  End-to-end unsupervised ML system: RFM features and K-Means clustering behind a FastAPI service on AWS EC2, used by a Streamlit web app and a native Android app.

• Credit Risk PredictorCase study

  Python, scikit-learn, HistGradientBoosting, pandas, Streamlit

  Gradient-boosted model on applicant financial, demographic and credit data, with a Streamlit app that returns default probability, risk class and the features driving the model.

  ROC-AUC 0.76; catches 41.8% of defaulters (recall) at a custom 15% threshold; 85.2% accuracy.

• Quanta (Sangam AI)LiveCase study

  Qwen2.5, Ollama, OpenWebUI, Nginx, DigitalOcean

  Self-hosted LLM chat platform running Qwen2.5 through Ollama and OpenWebUI, deployed on DigitalOcean behind Nginx with HTTPS and custom system prompts.

• NewsIntelLiveCase study

  Python, scikit-learn, TF-IDF, NLTK, Flask, Supabase, Google OAuth

  My final-year engineering project: an NLP platform that classifies news as real or fake with TF-IDF features, NLTK preprocessing and a Passive Aggressive classifier, served through Flask with Google sign-in and verification history on Supabase.

• Student Marks PredictorLiveCase study

  Python, scikit-learn, FastAPI, Pydantic, AWS EC2, Streamlit

  scikit-learn regression pipeline served from a FastAPI backend on AWS EC2 to a Streamlit app and an Android app in closed testing on Google Play (API design and Android app built with AI assistance).

• AI & ML RAG AssistantCase study

  Python, LangChain, FAISS, sentence-transformers, Streamlit

  Learning prototype of retrieval-augmented generation: LangChain chunking, MiniLM embeddings in a FAISS index, top-3 retrieval, and Gemini via OpenRouter answering only from the retrieved context.

• India Election 2024 DashboardLiveCase study

  Power BI, Data modelling

  Power BI dashboard with a data model for state-wise and constituency-level analysis, across four views: overview, state demographics, political landscape and constituency analysis.

Experience

• Independent AI/ML engineer, Self-directedOngoing

  Designing, building and shipping AI products: ProfilePilot (500+ downloads on Google Play), DealShield AI (Chrome Web Store), Quanta, NewsIntel, Customer Intelligence and more.

• Data science intern, IT VedantInternship

  Real-world ML projects in business insight, predictive modelling and data storytelling.

• Quantitative research, JPMorgan ChaseVirtual

  Financial data modelling and statistical research on market data.

• Data science, British AirwaysVirtual

  Predictive modelling of customer behaviour and an end-to-end ML pipeline.

• Data analytics, Deloitte AustraliaVirtual

  Data cleaning, visualisation and business insight for client deliverables.

• Data visualisation and GenAI, TataVirtual

  Power BI dashboards and business reporting.

• Retail analytics, QuantiumVirtual

  Customer analytics and statistical analysis for the grocery sector.

Education and certifications

• B.E. Computer Engineering, CGPA 7.25, CSMIT, University of MumbaiJune 2022 to May 2026
• Professional Certification, Data Science and Analytics with AI, IT VedantDecember 2025 to 2026
• Machine Learning with Python, IBM, via IT Vedant
• Data Analysis with Python, IBM, via IT Vedant
• Python 101 for Data Science, IBM, via IT Vedant
• Advanced Excel, SQL, Power BI and Python for Data Analytics, IT Vedant
• Machine Learning and NLP Bootcamp, Udemy2025
• Stock Market Course, Asmita Patel Global School of Trading2024