Performance & Debug Software Engineer – AI Inference

Responsibilities: — Profile and optimize end-to-end large language model (LLM) inference on custom AI accelerators. — Build benchmarks and regression tests for distributed inference and KV cache. Requirements: — Experience with LLM inference and performance optimization. — Knowledge of Linux performance tools and debugging. — Familiarity with C#, Triton, Python, Perfetto, FPGA, eBPF, HIP, ASIC, CUDA. Benefits: — Remote work opportunity. — Competitive salary range from $200,000 to $300,000. The position involves working with advanced AI inference technologies and requires expertise in profiling and debugging distributed systems and hardware accelerators.