jobs

Senior Inference Engineer, AGI

We are looking for a Senior Inference Engineer to own inference for real-time multimodalconversational AI. This is a full-stack inference role: you will work across the entire path a modeltakes from research to production — shaping model ar

Company

Amazon

Location

Sunnyvale, California, USA

Status

Closed

Posted

2026-08-27T00:00:00+00:00

Amazon is hiring a senior inference engineer to own inference for real-time multimodal conversational AI. The work spans the model path from research to production: architecture co-design with scientists, a low-latency streaming serving runtime under sub-second budgets, GPU kernels and quantization, multi-GPU inference, and offline rollout and reward-serving systems for reinforcement learning and evaluation. The posting asks for 2+ years optimizing neural-model inference, GPU performance knowledge, and a record of shipping latency-constrained production systems. Ownership runs end to end at frontier scale.