This role has closed. True Talent Solutions Partners has other openings below.
open-source language models
ABOUT THE ROLE
Join a small AI infrastructure team building efficient inference for open-source language models. You will improve performance and reliability across diverse hardware, helping make production AI faster and more cost-effective.
WHAT YOU'LL DO
- Deliver day-zero support for new open-source models, tuning them for latency and throughput.
- Optimize inference serving through batching, KV cache management, speculative decoding, and quantization.
- Write and tune kernels using CUDA, HIP, and Triton across a range of accelerator platforms.
- Design, deploy, and operate heterogeneous clusters across hardware vendors.
- Run production inference systems, improving reliability, observability, and cost per token.
- Work with customers and teammates to identify problems and shape technical solutions.
WHAT WE'RE LOOKING FOR
- Typically 1 to 6 years of experience in backend, infrastructure, systems, or related engineering work, including early-career candidates with strong internships.
- Strong computer science fundamentals, including computer architecture, memory hierarchy, and operating system internals.
- Systems engineering experience beyond application-level or web development, with ownership of challenging technical work.
- Familiarity with CUDA, Triton, GPU programming, or comparable low-level systems technologies; experience with HIP is useful.
- Experience with infrastructure at scale, such as clusters, data centers, or large GPU fleets, and familiarity with inference optimization techniques.
- Comfort using AI coding tools to improve e