GenAI Infra Engineer: Real-Time GPU Serving & Fine-Tuning

We are hiring a Software Engineer, Machine Learning Infrastructure to join a small, high-leverage team building production GenAI infrastructure at scale. The role focuses on real-time GPU serving, high-throughput batch inference, and model fine-tuning for open-weight platforms.

You will collaborate across model serving, inference engines, training pipelines, and observability, pushing cost/performance frontiers while meeting latency and reliability targets.