Member of Technical Staff
$200,000–$200,000 year
On-siteSan Francisco, California, United States
San Francisco, California, United StatesOn-siteFull Time$200,000–$200,000 yearSenior LevelStartup
Full TimeSenior LevelStartup
Job Summary
Ship day-zero support for new open-source models tuned for latency and throughput. Optimize the serving stack including batching, KV cache, and speculative decoding. Write and tune kernels in CUDA, HIP, and Triton across NVIDIA, AMD, TPU, and Trainium hardware. Design, deploy, and operate heterogeneous clusters while running production inference to manage reliability, observability, and cost per token at scale. Work on-site in San Francisco five days a week with complete autonomy to solve problems from customer interaction to custom GPU kernel development.
Required Qualifications
- Ship day-zero support for new open-source models, tuned for latency and throughput
- Optimize the serving stack: batching, KV cache, speculative decoding, quantization
- Write and tune kernels in CUDA, HIP, and Triton for NVIDIA, AMD, TPU, Trainium, D-Matrix, and more
- Design, deploy, and operate heterogeneous clusters across vendors
- Run production inference across a mixed fleet: reliability, observability, and cost per token at scale
- On-site in San Francisco
- Five days a week
Desired Qualifications
- Infinitely Resourceful
- Exceptionalism
- Unreasonable Standards
- Company Over Self
- High EQ
- Learns Quickly
- First Principles Thinker
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.