Description
Reducto is hiring an ML Infrastructure Tech Lead to own the technical direction and hands-on implementation of high-performance model training and inference infrastructure. The role focuses on optimizing model-serving kernels, GPU utilization, distributed systems, Kubernetes, reliability, observability, latency, throughput, and cost efficiency, while partnering with ML and Platform teams on architecture and capacity planning. It requires at least five years of production infrastructure and ML systems experience, strong Python and systems-engineering skills, and the ability to lead ambiguous technical projects. The position is fully in-person at Reducto’s San Francisco office and includes medical, dental, and vision insurance.
