Client Roles
ABOUT THE ROLE
Join a small AI infrastructure team working to improve the performance and efficiency of large language model inference. You will contribute across software systems, GPU kernels, and production deployments, helping deliver fast, reliable inference across diverse hardware.
WHAT YOU'LL DO
- Bring support for new open-source models to production, tuning them for latency and throughput.
- Optimize inference serving, including batching, KV caching, speculative decoding, and quantization.
- Write and tune GPU kernels using CUDA, HIP, and Triton across varied hardware platforms.
- Design, deploy, and operate heterogeneous compute clusters.
- Maintain production inference systems, with a focus on reliability, observability, and cost efficiency.
- Work autonomously on technical problems and collaborate with customers and teammates to guide solutions.
WHAT WE'RE LOOKING FOR
- One to six years of software engineering experience, including systems or low-level engineering close to hardware.
- Strong understanding of computer architecture, memory hierarchy, and operating system internals.
- Experience with backend, infrastructure, or systems work, as well as familiarity with Python and GPU programming tools such as CUDA or Triton.
- Background in machine learning inference optimization or operating large-scale infrastructure, such as clusters or GPU fleets, is valuable.
- Evidence of strong technical ownership, rapid learning, and effective problem-solving; customer-facing experience is also useful.
- Uses AI agents or coding tools to improve