Senior GPU Inference Kernel Engineer - Fast & Efficient AI

Vidman AI; Stati Uniti; Remoto; USD 140.000 - 210.000; Tempo pieno

Descrizione del lavoro

Vidman AI is seeking a senior systems engineer to accelerate open-model inference performance by optimizing GPU kernels, memory usage, and production runtimes. Your work will be measured by latency reductions and token cost improvements.

You will operate across low-level performance engineering and deployed serving systems, collaborating with research and platform engineers to support new model architectures and deliver upstream changes.

Competenze

• 5+ years in systems software or ML systems engineering with hands-on GPU work.
• Strong C++ and Python with deep CUDA/Triton/CUTLASS experience.
• Experience profiling hardware and interpreting low-level GPU behavior.
• Familiarity with modern inference runtimes like vLLM or TensorRT-LLM.
• Demonstrated kernel optimization with before-and-after measurements.

Mansioni

• Build and tune kernels for attention, matrix multiplication, and normalization.
• Improve data movement through cache reuse, KV-cache management, and operator fusion.
• Implement low-precision inference paths, including INT4, FP8, and INT8, for available hardware.
• Profile GPU execution, inspect PTX or SASS where needed, and ship optimizations.
• Integrate improvements into inference runtimes and contribute upstream.
• Coordinate with research and platform engineers to support new model architectures.

Conoscenze

C++ performance engineering

Python

CUDA/Triton/CUTLASS

GPU profiling

ML systems

Strumenti

CUDA

TensorRT-LLM

vLLM

Descrizione del lavoro

Vidman AI is seeking a senior systems engineer to accelerate open-model inference performance by optimizing GPU kernels, memory usage, and production runtimes. Your work will be measured by latency reductions and token cost improvements.

You will operate across low-level performance engineering and deployed serving systems, collaborating with research and platform engineers to support new model architectures and deliver upstream changes.