Senior Software Engineer - AI Inference Performance

What you’d do

Analyze and optimize LLM and VLM inference performance, including latency, throughput, and KV-cache capacity. Profile workloads with Nsight and PyTorch tools and tune serving techniques like batching, quantization, and speculative decoding. Full time, based in Santa Clara, CA. Found on the employer's careers page on Sep 29, 2026. Apply through the link.