Open It UpNow Playing
LearnApp - Core Team MemberI joined LearnApp as a college student because I believed that financial education was broken in India and the only way to bring change in financial habits was through education.
Designed library of investing and finance courses50% course completion rate (category average: ~10%)₹1.2Cr ARR
IND MONEY - ASSOCIATE PRODUCT MANAGERJoined INDMoney because I realised that while financial education was important, it only changes what people know. But the real leverage in personal finance is at the moment of decision when you're buying a product, not before it.
Built financial planning module with recommendation algorithms — 4–5 hours to 15 minutes per planEnabled 20,000+ advisory plansBuilt personalized insurance recommendation engine aligned to user goals — ₹1.5Cr ARR in year one
ET Money - Product ManagerMy time at ET Money taught me one thing about AI products: the model is interchangeable, the eval is the product. The rubric is where the judgment lives. That experience continues to shape how I build.
Built AI support automation — 19K to 9K monthly tickets, a 55% reduction, and 30% CSAT improvementBuilt 0-to-1 offline distribution business — 12% of SIP book, 10% of gross sales within 4 monthsBuilt Loan Against Mutual Funds from zero — ₹100Cr disbursals in 7 monthsLed ET Money Earn from 0 to ₹300Cr AUMBuilt execution-only Mutual Fund Platform — projected ₹10Cr annual revenue
Paytm Money - Sr. Product ManagerI joined Paytm Money in July 2026. My current focus is on building agents and improving the overall app experience.
Working on agentsImproving the overall app experience
EMBEDDINGS | INTENT ROUTING | CHROMADB
Semantic search engine across 16,197 mutual funds with intent-aware routing.
Routes queries into lookup, comparison, or filtered discovery.Handles typos, partial names, categories, and investment styles.Generates fund analysis across returns, risk, and expense ratios.
AGENTS SDK | SSE STREAMING | JD PARSING
ChatGPT-style hiring assistant for recruiters to evaluate fit from a company URL, JD, upload, or question.
Built a standalone chat interface with zero-state prompts, persistent composer, file chips, and streamed responses.Shipped a V3 agent pipeline with intent planning, optional company research, evidence gathering, and intent-specific answer agents.Kept V1, V2, and V3 eval history visible so quality, fit calibration, and latency tradeoffs can be compared over time.Supports PDF, DOCX, and TXT job descriptions with structured SSE final events for fit-level UI.
