Research Engineer - Inference

Highlights

• Turn research breakthroughs into real-time products used by millions.
• Own systems serving frontier AI models fast, reliably and at scale.
• Build tooling that ships new models to production quickly and safely.

What they offer

• Annual discretionary learning and development stipend
• Annual discretionary social travel stipend to meet colleagues
• Annual company offsite in a new location
• Monthly co-working stipend if not near a hub

Ideal candidate

An autonomous, impact-driven engineer who loves turning research breakthroughs into fast, reliable products. You obsess over performance at scale and thrive owning systems end-to-end.

Requirements

• Experience deploying and serving ML models in production for latency-sensitive applications
• Strong GPU programming and inference optimization skills (CUDA, Triton, TensorRT, vLLM, SGLang)
• Ability to autonomously profile, diagnose and eliminate bottlenecks across the serving stack
• Track record solving hard problems shown via projects, designs or GitHub contributions