Member of Technical Staff

About the Role

Join a small AI infrastructure team building systems that improve the performance and efficiency of large language model inference. You will work across model serving, GPU kernels, and heterogeneous computing infrastructure, with ownership of problems from customer needs through production deployment.

What You'll Do

• Deliver day-one support for new open-source models, tuning them for latency and throughput.

• Improve model serving through batching, KV cache management, speculative decoding, and quantization.

• Write and tune kernels using CUDA, HIP, and Triton across a range of accelerator hardware.

• Design, deploy, and operate clusters across multiple hardware vendors.

• Run production inference on mixed hardware fleets, focusing on reliability, observability, and cost efficiency.

• Work with customers to understand performance needs and help set technical priorities.

What We're Looking For

• Typically 1 to 6 years of experience in backend, infrastructure, systems, or low-level engineering, including experience at scale or ownership of complex systems end to end.

• Strong understanding of computer architecture, memory hierarchy, and operating system internals beyond application-level development.

• Hands-on experience with CUDA, HIP, Triton, or other GPU programming, plus Python and familiarity with accelerators such as TPUs or AWS Trainium.

• Knowledge of ML inference optimization techniques such as quantization, batching, KV caches, and speculative decoding.

• Strong computer science fundamentals, demonstrated problem-solving ability, and interest in applying AI coding tools to improve engineering workflows.

• Comfort communicating with customers and working across both systems engineering and broader software development.

Compensation & Benefits

Base salary is $200,000 to $300,000 USD annually. Visa sponsorship is available.

Location

On-site in San Francisco, California, five days per week.