Software Engineer → Product Manager
UCLA Anderson MBA '28. Former Senior SWE at Visa. Building enterprise products at the intersection of data, automation, and user-centered design.
About
I spent four years as a Senior Software Engineer at Visa, helping launch V-ARM — Visa's first B2B accounts receivables product.
Before that, I earned an M.S. in Computer Science (ML specialization) from Columbia University and a B.Tech. in CS from NIT Trichy. I'm now joining UCLA Anderson's MBA program to make the full transition into product management.
I'm currently building a portfolio of enterprise products — working in public, shipping fast, and documenting the product decisions.
Product Demos
Each demo shows the user problem, my PM approach, and measurable outcomes. Click to explore the full product story.
Finance teams spent 10+ hours/week manually tracking $2.4M in overdue accounts across spreadsheets and email.
Co-defined MVP with 12 enterprise customers. Built automated aging reports, payment prediction, and smart follow-up workflows.
85% reduction in manual work · $340K recovered in Q1 · 94% customer satisfaction
Product managers spent 2 hours reviewing each Business Requirements Document for clarity, completeness, and edge cases.
Built multi-agent AI pipeline using Claude API to score BRDs across 12 dimensions with section-level feedback and improvement suggestions.
2 hours → 2 minutes · 60x faster · 40% improvement in first-pass quality
Finance teams often receive payment instructions through messy email threads, forwarded invoices, and informal reminders. Manual extraction creates delays and increases the risk of missing due dates, vendors, or payment methods.
Built an internal finance tool that accepts .txt and .eml email uploads, extracts payment instructions using structured outputs, and stores results in PostgreSQL for review. The Streamlit interface gives operators a simple workflow: upload, inspect, and review extraction history.
Reduces manual data entry · Handles multiple payment requests per email · Improves extraction reliability
All Projects
01
Intelligent extraction of structured payment data from unstructured emails — improving accuracy and reducing manual data entry for accounts payable teams.
02
Intelligent scoring of product requirements documents across clarity, completeness, edge-case coverage, and acceptance criteria quality.
03
Intelligent classification of payment disputes by type, resolution path, and regulatory flag — with confidence thresholds for human review.
Education
Experience
Technical fluency
Get in touch
I'm open to PM opportunities and conversations with founders building at the intersection of data and enterprise software.