← Back to the portfolio
Tech Lead · UM6P (SCI) · 2025–now

Fifty users to a thousand.

Led 5 engineers rebuilding a research LLM platform into Aideator, a production system.

Senior R&D Engineer · Technical Lead of a 5-person cross-functional team · Oct 2025 – present

20×capacity
Preservedall historical data
5engineers led

Context

Deliberatorium is a UM6P research platform that uses LLMs to structure large-scale deliberation. It existed as research code. I lead its rebuild into Aideator, a production system.

Problem

The legacy system topped out around 50 concurrent users, its research concepts weren't productised, and years of historical deliberations had to survive the move.

Architecture

ParticipantsReact · TypeScript clientFastAPI · LLM features
Legacy Deliberatorium dataMigration & ingestion
PostgreSQL · Redis
Docker Compose on DigitalOcean · CI · code review

Key decisions & trade-offs

01

Re-architect, don't patch

Rebuilt the full stack on React/TypeScript, FastAPI, PostgreSQL and Redis.

Trade-offMore work up front than incremental fixes, in exchange for removing the scaling ceiling.

02

Migrate the history

Owned the end-to-end migration, ingesting historical data while re-implementing research-paper concepts as production LLM features.

Trade-offA harder migration than starting fresh, but research continuity is the platform's value.

03

Standards before features

Set Docker-based deploys, code review and CI practices, adopted as the default across the project.

Trade-offSlower first weeks; every engineer after that ships the same way.

Outcomes

ReactFastAPIPostgreSQLRedisDocker