Description
Nuance Labs is hiring a senior AI inference optimization engineer to own end-to-end optimization of LLM, audio, and diffusion-model inference for a real-time, full-duplex multimodal system. The role focuses on KV cache strategies, serving frameworks such as vLLM and SGLang, latency and throughput profiling, quantization, CUDA or Triton kernel optimization, and internal optimization tooling. Candidates should have significant production or high-traffic inference experience, strong Python and PyTorch skills, and familiarity with inference acceleration techniques. The position is in-person in Seattle five days per week and offers $250,000–$350,000 base salary plus equity and visa sponsorship.
