Research Engineer, Inference
Polished Snow · Posted Nov 3, 2026
- Palo Alto, California, United States
Build and deploy inference systems for AI models in critical infrastructure.
Responsibilities
- Own the path from a research checkpoint to a deployed model
- Build the serving infrastructure and make new models straightforward to ship
- Profile and improve latency, throughput and cost across the inference stack
- Evaluate quantization, distillation, KV-cache optimization and batching
- Build and tune serving systems for low-latency, real-time and streaming workloads