Member of Technical Staff, AMD GPU Performance Engineering

Mindsource • San Francisco, CA

1d

About The Position

Mindsource is seeking an AMD GPU Performance Engineer for a direct client. The role focuses on making vLLM a first-class inference engine across the AMD accelerator ecosystem. The engineer will build and optimize AMD GPU backends, kernels, runtime paths, and benchmarking infrastructure using ROCm, HIP, Triton, CK, AITER, and related tools. The work spans inference systems, kernels, compilers, and hardware architecture, improving performance-critical paths such as attention, GEMM, sampling, KV cache, and communication-heavy operations. The goal is to make AMD GPU support in vLLM usable, fast, benchmarked, and maintainable.

Requirements

• Bachelor's degree or equivalent experience in computer science, engineering, systems, machine learning, or a similar field.
• Hands-on experience optimizing AMD GPU workloads using ROCm, HIP, Triton, CK, AITER, or similar AMD ecosystem tools.
• Deep understanding of AMD GPU execution, memory behavior, toolchains, kernel performance, and backend-specific performance constraints.
• Experience optimizing ML kernels or inference paths such as attention, GEMM, sampling, KV cache, fused kernels, or communication-heavy runtime paths.
• Strong performance profiling and benchmarking skills, including using measurements, hardware counters, correctness tests, and reproducible benchmarks to guide optimization work.

Nice To Haves

• Experience with vLLM, SGLang, TensorRT-LLM, ROCm-based serving, or other LLM inference systems.
• Familiarity with batching, KV cache, decoding, serving tradeoffs, and backend performance constraints in production inference systems.
• Experience with compiler and kernel technologies such as Triton, MLIR, LLVM, CK, AITER, HIP, or other kernel DSLs and backend libraries.
• Knowledge of quantization methods such as INT8, FP8, mixed precision, or AMD hardware-specific numeric formats, including accuracy and performance tradeoffs.
• Contributions to vLLM, ROCm, HIP, Triton, CK, AITER, PyTorch, compiler projects, or other open-source ML infrastructure.
• Experience building AMD GPU benchmarking infrastructure or automated performance regression detection for accelerator workloads.
• Experience working directly with AMD, accelerator platform teams, or early-access programs to ship backend, compiler, or inference performance improvements.

Responsibilities

• Build and optimize AMD GPU backends, kernels, runtime paths, and benchmarking infrastructure for vLLM.
• Improve performance-critical paths including attention, GEMM, sampling, KV cache, and communication-heavy operations.
• Use profiling, hardware counters, correctness tests, and reproducible benchmarks to guide optimization work.
• Help make AMD GPU support in vLLM usable, fast, benchmarked, and maintainable.

What This Job Offers

• Job Type: Full-time