Product Manager · AI, Legal & Data-Heavy Products
Founding PM at Proxity, where I architected and shipped a production AI due-diligence engine. Before that: scaled a legal-media platform to 150K MAU and $500K ARR. Ex-lawyer with 5 years in insolvency and banking law.
A production multi-agent pipeline for investment due diligence: 13 stages, cited facts, human-in-the-loop review. Agentic loops only where they earn their place.
A self-enriching market-intelligence graph for asset deals: an AI pipeline drafts, a human editor decides, and every decision feeds back into the graph.
Built the product organization from scratch, monetized the B2B side with a custom CRM, then returned as a consultant to ship AI automation across the operation.
Designed the methodology, personally ran the interviews, and turned raw market data into a top-30 ranking and a public B2B analytics platform for international investors.
Analysed how lawyers actually worked, then shipped document automation, analytics API integrations, and a knowledge portal for 200+ employees.
Hi! I'm Ilia. What drives me as a Product Manager is seeing technology actually help people - making a complicated task feel simple or giving someone back valuable time.
My path here wasn't typical. I started as a corporate and banking lawyer in Russia and spent five years on insolvency cases. I moved into product because I kept running into the same thing: huge amounts of legal work that could be structured, automated, and turned into software - but nobody at the intersection was building it. So I became that person.
Since then I've been the operational lead who built a startup's processes from zero to $500K ARR, the PM behind products used by 150,000+ people monthly, and most recently the founding product hire shipping production LLM-agent systems. I've worked hands-on with generative AI since 2022 - not pitching it, building it: pipelines, guardrails, failure modes and all.
My approach: dig into the "why" behind a problem before jumping to solutions, use data to see the full picture, and bring honest trade-offs to the table. I'm based in Valencia, Spain, with full work authorization, and I'm most at home building at the intersection of law, AI, and regulated complexity.
Two merged pull requests to the AI reading-assistant plugin for KOReader: smarter context retrieval, full-sentence translation, and instant translation on text selection. Started as reading sci-fi in English, ended as shipped features.
A Firebase app that turns a rough research question into a precise Deep Research prompt through AI-generated clarifying questions - a pre-research step that saves 10-15 minutes of prompt tweaking per report.
Closing talk of the QA Breakfast Valencia season (RingCentral, June 2026): what AI-speed building does to product judgment - argued through two features I shipped myself, including one merged with zero review changes.
The system behind 70-80% agent-written code with 100% human-owned architecture and review: blocked git push, ADRs as context, and honest numbers on what changes.
Hands-on notes on prototyping and applied AI: prototyping with Firebase, what got cheap and what got expensive in AI-speed building.