I build AI systems that run in production
From sensor signal pipelines to LLM agents, I design, deploy and operate AI systems that actually run in production.
I decide technical choices on measurable evidence, and I treat finding the failures after shipping as half the job. My master's research (graph neural networks for behavior classification) maps directly onto my current work (IMU behavior analysis).
4.4×inference pipeline throughputmeasured on 24h real-animal data · 2.16M rows
10papers · talks3 journal · 6 conference · 1 in preparation
4y 5min production AIsince 2022.04
Selected Work
Behavior Classification Inference Pipeline — 4.4× Throughput
Reworked the production core package that extracts 903 features from 6-axis IMU raw signal, for 4.4× throughput and 3.3× end-to-end speedup.
4.4×throughput24h real-animal · 2.16M raw rows
423win/sec8,640 windows · was 96
208 / 0pass / failfull suite · output-equivalence verified
Internal LLM Data Agent Platform
An assistant that answers questions about internal data in natural language. Moved from MVP to a tool-calling agent, with the architecture decided by A/B measurement.
5 / 5compound queriesown eval set · old structure 0/5
730schema documents95 tables · 635 columns
4surfacesMCP · Slack · REST · app API