Loading
AI Platform Engineer | LLM Infrastructure, RAG Systems & Distributed Workers | FastAPI, Python, RabbitMQ, Redis | Founding Engineer @ Lexomat
VerifiedFounding Engineer who shipped a production AI legal-tech from 0→1. Scaled a fault-tolerant RAG pipeline to query over 4.5M+ documents. Proven track record of accelerating product velocity, including a solo 15-day React migration that cut page load times by 66% (3s→1s) and architecting high-throughput distributed backend infrastructure serving 10,000+ DAU.
Jan 2025 — Present
Remote · full time
Architected and shipped a production AI legal-tech from 0→1, owning the entire stack from infrastructure to frontend. Engineered a high-throughput RAG pipeline (FastAPI, pgvector) querying against a highly optimized vector database scaled to over 4.5+ million legal documents and embeddings. Engineered a cloud-native, asynchronous orchestration layer using TaskIQ and Redis, decoupling high-latency LLM workflows to guarantee zero data loss and system stability during client-side disconnects. Architected a continuous evaluation CI/CD pipeline featuring automated E2E testing for non-deterministic LLM workflows, establishing strict guardrails against prompt regressions and retrieval failures. Integrated Stripe billing and automated invoice generation system using headless browser rendering and backend automation pipelines. Orchestrate the full system lifecycle—from architecture design to deployment and monitoring—ensuring high production reliability and rapid bug resolution.
Want a profile like this one? Build yours in a single chat, then start applying.
Create your profile