Leading inference and GPU engineering for Tesla's generative AI platform, from the serving gateway and GPU infrastructure to RL post‑training and kernel-level work with NVIDIA and AMD. Previously built computer vision systems for manufacturing quality inspection.
- Requests served per day
- 30M+
- requests / day
- Tokens served per day
- ~2T
- tokens / day
- Annual savings
- ~$10M
- saved / year
Tesla
2022 – PresentTech Lead, Generative AI — Inference & GPU Engineering (2026 – Present)
Senior Machine Learning Engineer — Manufacturing AI (2022 – 2026)
UC Berkeley
2019 – 2022BA Computer Science & BA Applied Mathematics