About this role
Principal LLM Inference Engineer at d-Matrix. Location: Santa Clara, California, United States. Role: optimizing kernels, building runtimes, prototyping deployments Requirements: Bachelor's in CS/EE (or equivalent) with 10+ years experience (Master/PhD with 6+ years preferred); strong Python and C/C++; experience optimizing LLM inference, quantization, batching, GPU kernel programming and contributor-level work on inference frameworks. Category: Engineering Seniority: Senior Level Tools: Python, C, C++, vLLM, SGLang, TensorRT-LLM, ONNX Runtime, CUDA, Triton, JAX Commitment: Full Time Workplace: Hybrid Languages: English