JOBSEARCHER

ML Engineer: Onsite LLM Inference & Speculative Decoding

Early-Stage AI Startup in Mountain View is seeking a Machine Learning Engineer to advance LLM inference and speculative decoding on real-world AI workloads. You will work on model distillation, optimization and efficient inference at scale with a small, highly technical founding team. Ideal candidates have 2+ years of hands-on ML engineering, fluent Python and PyTorch, and experience with speculative decoding, vLLM or similar serving frameworks.