System Engineer (Token Factory)
Core
Develop and optimize low-level kernels and runtime components for AI inference on massive GPU clusters to make foundation models fast and reliable.
Role type
Senior IC systems engineer (GPU inference)
Builds
High-performance inference engines for text, vision, audio, and multimodal models
Domain
Cloud infrastructure + AI inference
Deliverable
production ML models
Required skills
C++, GPU programming, low-level high-performance coding, memory management, systems-level software development, profiling and debugging, CPU/GPU architecture knowledge
Preferred skills
CUDA, ROCm, CUTLASS, Triton, TensorRT, TVM, Linux internals, perf/VTune/Nsight, vLLM/sglang/TGI
Technologies
CUDA, ROCm, CUTLASS, Triton, TensorRT, TVM, Linux, perf, VTune, Nsight
Responsibilities
Develop and optimize low-level kernels and runtime components for AI inference; Improve performance of inference engines on GPU platforms; Profile and debug system-level and hardware-level performance issues; Integrate support for new hardware architectures (Hopper, Blackwell, Rubin); Collaborate with ML and backend teams to optimize end-to-end execution
Seniority
Senior, hands-on IC
