Member of Technical Staff, TPU & AMD GPU Performance Engineering Job at Inferact, Remote

NisvekJjTVI4VFhXMEdJY0RzMjhJRkFreUE9PQ==
  • Inferact
  • Remote

Job Description

Role Description

We're looking for a TPU and AMD GPU performance engineer to make vLLM a first-class inference engine across non-NVIDIA accelerators. Frontier inference cannot be locked to one hardware stack. As AMD GPUs, TPUs, and other accelerators become increasingly important, vLLM needs backend paths that are fast, correct, benchmarked, and maintainable across heterogeneous hardware platforms.

  • Build and optimize AMD GPU and TPU backends, kernels, compiler integrations, runtime paths, and benchmarking infrastructure.
  • Work at the boundary of inference systems, kernels, compilers, and hardware architecture.
  • Improve paths such as attention, GEMM, sampling, KV-cache, communication-heavy operations, and model serving on non-NVIDIA hardware.
  • Your work will directly impact how broadly and efficiently the world can run AI inference with vLLM.

Qualifications

  • Bachelor's degree or equivalent experience in computer science, engineering, machine learning systems, hardware systems, compilers, or similar.
  • Hands-on experience optimizing workloads on AMD GPUs, TPUs, or another non-NVIDIA accelerator stack.
  • Experience with AMD ecosystem tools such as ROCm, HIP, Triton, CK, AITER, or equivalent GPU performance libraries and tooling.
  • Experience with TPU, XLA, JAX, Pallas, or related compiler and runtime tooling for accelerator workloads.
  • Ability to optimize ML inference paths such as attention, GEMM, sampling, KV-cache, fused kernels, backend runtimes, or communication-heavy operations.
  • Strong performance profiling and benchmarking discipline, including tokens/second, latency, throughput, correctness parity, hardware counters, and reproducible measurement methodology.
  • Ability to navigate immature tooling, incomplete documentation, backend-specific rough edges, and cross-platform performance differences without getting stuck.

Requirements

  • Experience with vLLM, SGLang, TensorRT-LLM, ATOM, JAX-based serving framework, or other LLM inference systems.
  • Deep understanding of inference architecture and serving tradeoffs, including batching, KV-cache, decoding, prefill/decode scheduling, and backend performance constraints.
  • Experience with compiler technologies such as XLA, MLIR, LLVM, Triton, Pallas, or other compiler/kernel DSLs, including lowering, fusion, and backend code generation.
  • Knowledge of quantization techniques such as MXFP8, MXFP4, mixed precision, or hardware-specific numeric formats, and the ability to reason about accuracy/performance tradeoffs.
  • Experience with distributed inference performance, including communication, memory movement, hardware topology, and scale-out bottlenecks across multi-accelerator workloads.
  • Open-source contributions to vLLM, JAX/XLA, ROCm, Triton, PyTorch, compiler projects, or related ML systems infrastructure.

Benefits

  • Generous health, dental, and vision benefits.
  • 401(k) company match.

Logistics

  • Location: This role is based in San Francisco, California. Will consider remote in the US for exceptional candidates.
  • Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.
  • Visa sponsorship: We sponsor visas on a case-by-case basis.

Job Tags

Full time, Remote work, Visa sponsorship

Similar Jobs

MileHigh Adjusters Houston Inc

Independent Insurance Claims Adjuster in Saint Petersburg, Florida Job at MileHigh Adjusters Houston Inc

 ...Insurance Claims Adjuster? With continued storm activity and catastrophic weather events across the country, experienced and properly trained adjusters continue to be in demand. MileHigh Adjusters Houston works with both: Experienced licensed adjusters seeking... 

Unknown Planner

Campus Recruiter Job at Unknown Planner

 ...The Campus Recruiter is responsible for developing and executing recruiting strategies focused on building talent pipelines through colleges, universities, trade and technical schools, military organizations, and other targeted talent communities. This role builds relationships... 

City of Lompoc

Tree Trimmer Job at City of Lompoc

 ...removal of trees; and perform other specifically related work as required. CLASS CHARACTERISTICS: Positions in the class of Tree Trimmer perform -the working level class in tree maintenance operations. Individuals initially perform manual labor and tree trimming work... 

Dayton Freight

Summer Management Internship Path to Trainee Program Job at Dayton Freight

 ...Dayton Freight Lines offers a summer Management Interns program, a 9-week accelerated internship in the Transportation industry in Cedar Rapids, IA. Participants may be considered for the Dayton Freight Management Trainee Program after completing their degree. The... 

Omni Inclusive

Computer System Validation Engineer Job at Omni Inclusive

 ...Manufacturing It Systems Quality & Compliance Specialist Cell Therapy Manufacturing SystemsThe Manufacturing IT Systems Quality...  ...IT deviations, CAPAs, Investigations, Change Management, computer system validation in support of the vector manufacturing site. The candidate...