Machine Learning Engineer
Machine Learning Engineer – LLM Inference & Speculative Decoding
Location: Mountain View, CA | Onsite
Company:
- Early-Stage AI Startup
- We're partnering with an exciting early-stage AI startup founded by engineers with backgrounds building
- Google's TPU and Tesla's Dojo Supercomputer .Backed by strong early investor interest, the team is building software to tackle one of AI's biggest challenges:making AI inference faster, cheaper and significantly more energy-efficient.
- Joining a small, highly technical founding team, you'll have the opportunity to take real ownership of core ML technology, working at the intersection of model training, inference infrastructure and GPU performance.
What we’re looking for:
2+ years of hands-on ML engineering experience.
Strong Python/PyTorch and model training or distillation experience.
Knowledge of speculative decoding, LLM inference and model optimisation.
Experience with vLLM, SGLang or super serving framework.
Work alongside engineers behind some of the world's most advanced AI compute systems, with significant technical ownership and the opportunity to help shape the future of efficient AI infrastructure.