Real-time routing & experimentation engine
Every user is scored across 10+ lenders and sent to the one most likely to say yes, instead of walking a fixed funnel.
- 1.8× value per user
- 0 engineering support
I build products where mistakes are expensive.
Consumer credit, trading systems, government transactions. Four years across three industries where the model, the money and the regulator all have to agree.
I'm a product manager who builds - I write the decision logic, wire up the systems it depends on, and ship the screen the user sees.
$1B+Investment decisions informed · D. E. Shaw
4Public transactions closed · Ministry of Finance
₹15 CrMonthly lending run-rate built · Bachatt
2,000×Firm-wide data cost reduction
yes, really
Things I built.
Shipped, not specified.
Underwriting on data nobody was using
Most Indian applicants have no borrowing history, so the models read bank statements, SMS and app usage too.
- 30L+ customers
- Approvals +50%
AI agents for funnel forensics
When a funnel breaks, these agents read code, logs, events and user records in parallel and come back with the cause.
- MCP servers
- Parallel tracing
Proof of work.
PRDs and prototypes.
PrototypeProduct, Lending
Right lender at first try
Laid down the inception with eligibility gating. Built into a sophisticated recommendation system, with ML models powering decisioning and lifting user approvals.
Open
PRDYour role here
Title of the document
One line on the decision it settles.
Read
PRDYour role here
Second document
One line on the decision it settles.
Read
View more
Three very different rooms.
A lending app, a trading floor, and a ministry. In all three, the cost of a wrong decision showed up in someone’s money.
- 2026
- 2025
- 2024
- 2023
- 2022
May 2025 - now
Product Manager, Lending
Bachatt App · Consumer fintech
- Sole PM, reports to the CEO
- ₹15 Cr/month in 5 months
- 10+ NBFC partners
- Approvals +50%
- 30L+ underwritten
Sep 2024 - Apr 2025
Associate Project Manager
Ministry of Finance (DIPAM) · Government
- 4 transactions closed
- ₹5,000 Cr IREDA QIP
- RINL · NMDC–KIOCL · Mazagaon Dock
- Structuring through close
- Advised the Joint Secretary
Jul 2022 - Sep 2024
Associate Product Manager, Trading and Data Platforms
D. E. Shaw · Quant finance
- +12% earnings capture
- $1B+ influenced
- 28+ dashboards
- Pipeline 2 days → 3 hours
- 200+ hours/month automated
In the press.
Things I worked on that made the news.