Notes from building AI systems in production.
Short write-ups of decisions I made on real projects: what I chose, why, and what it cost.
- 3 Oct 2026 · 3 min read
Answers that trace back to a source
Why I grounded a fintech's LLM agents in a Neo4j knowledge graph instead of relying on vectors alone.
- 3 Oct 2026 · 3 min read
Run inference on the device, not in the cloud
Moving real-time YOLO detection from cloud servers to NVIDIA Jetson devices for a smart-city digital twin.
- 3 Oct 2026 · 3 min read
From research code to 1,000 users: rebuild, don't patch
Leading a 5-engineer team to turn a research LLM platform into Aideator, a production system with 20× the capacity.