Staff Technical Lead for Inference & ML Performance

Responsibilities

• Set technical direction for team working on kernels, applied performance, ML compilers, and distributed inference to build high-performance inference solutions.
• Provide hands-on IC leadership by contributing to critical inference performance enhancements and optimizations.
• Collaborate with research and applied ML teams to influence model inference strategies and deployment techniques.
• Drive advanced performance optimizations including model parallelism, kernel optimization, and compiler strategies.
• Mentor and scale team of performance-focused engineers.

Requirements

• Deep experience in ML performance optimization for large-scale generative models in production.
• Expertise in full ML performance stack: PyTorch, TensorRT, TransformerEngine, Triton, CUTLASS kernels.
• Expert knowledge of inference techniques: quantization, kernel authoring, compilation, model parallelism (TP, context/sequence parallel, expert parallel), distributed serving, profiling.
• Lead from the front as a respected IC who enjoys hands-on problem-solving.
• Thrive in cross-functional collaboration with ML teams, researchers, and stakeholders.

Nice-to-haves

• Experience building inference engines for diffusion and generative media models.
• Track record of industry-leading performance improvements (papers, open-source, benchmarks).
• Leadership experience in scaling technical teams.