Senior Principal ML Engineer — Inference Frameworks (Onsite)

Memwize is a VC-backed stealth-mode startup located in Sunnyvale, CA, seeking a Senior/Principal Machine Learning Engineer to drive performance improvements in inference frameworks and develop advanced cluster scheduling algorithms. The role focuses on optimizing throughput and latency for rack-level AI inference systems, working with vLLM, SGLang, and PyTorch in a hands-on capacity. Onsite full-time in Sunnyvale, CA with collaboration across ML and infrastructure teams.