Research Engineer - Inference

Highlights

• Own systems turning research breakthroughs into real-time products used by millions.
• Optimize inference for latency, throughput, and cost at massive scale.
• Build tooling that lets researchers ship 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 team offsite in new locations
• Monthly co-working stipend if not near main hubs

Ideal candidate

A deeply curious, autonomous builder who thrives on hard performance problems and turning research breakthroughs into fast, reliable products used by millions.

Requirements

• Experience deploying and serving ML models in production, ideally for latency-sensitive or real-time applications
• Strong engineering skills in GPU programming and inference optimization (e.g., CUDA, Triton, TensorRT, vLLM or SGLang)
• Capacity to autonomously profile, diagnose, and eliminate bottlenecks across the serving stack and build tooling to measure it