Client Roles
ABOUT THE ROLE
Join a small AI infrastructure team working to improve the speed and efficiency of large language model inference. You will build and operate systems that optimize models across a range of hardware, with ownership spanning low-level engineering and production operations.
WHAT YOU'LL DO
- Deliver day-one support for new open-source models, tuning them for latency and throughput.
- Improve inference serving through techniques such as batching, KV caching, speculative decoding, and quantization.
- Write and optimize GPU kernels using CUDA, HIP, and Triton across diverse accelerator platforms.
- Design, deploy, and operate heterogeneous clusters across hardware vendors.
- Run production inference across mixed hardware fleets, improving reliability, observability, and cost per token.
- Work directly with customers as part of solving infrastructure and performance challenges.
WHAT WE'RE LOOKING FOR
- Typically 1 to 6 years of experience in backend, infrastructure, systems, or related engineering work; strong early-career candidates are welcome.
- Strong understanding of computer architecture, memory hierarchy, and operating system internals beyond application-level development.
- Experience with low-level or systems engineering, plus familiarity with Python and GPU programming tools such as CUDA or Triton; HIP experience is also relevant.
- Knowledge of ML inference optimization, including quantization, batching, KV caches, or speculative decoding.
- Experience deploying or operating large-scale infrastructure, clusters, data centers, or