Fundraising Intelligence Platform
A fundraising workflow that brings voice onboarding, document extraction and investor matching into one platform.
Key decision
Match in layers: SQL filters narrow ~47K investors to a few thousand, vector search picks the top 30, and only then does the model write the report.
My contribution
Lead engineer across the frontend, backend and cloud for a fundraising advisory platform.
The constraint
Investor matching must narrow a large candidate pool before asking the model to generate a report.
How it works
A multilingual Gemini Live agent collects founder context. Document extraction feeds SQL filters over ~47K investors, pgvector selects the top 30, and the model produces a report. The platform also creates valuation memos and secure investor share links.
The result
Live in production, with onboarding, matching and investor-facing sharing in one workflow.