- San Mateo, California, United States
- Hybrid
- Full-time · Lead
First developer advocate to act as the technical voice on inference, focusing on open weight models, hardware, and applications.
Responsibilities
- Advance the technical conversation through original work on how inference behaves in production.
- Write CFPs and give talks at conferences, meetups, podcasts and panels.
- Work with labs and chip makers to launch new models and build integrations.
- Teach via technical blogs, notebooks, sample apps, and video walkthroughs.
- Bring developer feedback back to product and engineering to improve the self-serve experience.
Requirements
- Nice to have: vLLM
- Nice to have: SGLang
- Nice to have: Accelerators beyond NVIDIA
- Nice to have: Benchmark methodology
- Nice to have: ML or systems research background