Engineering Manager, Inference Performance & GPU

Baseten in San Francisco seeks an Engineering Manager for the Inference Performance team. You will lead engineers focused on making AI workloads faster on GPUs, including kernels, scheduling, batching, and KV-cache management. This role blends technical depth with people leadership to deliver high-impact optimizations. You will define the team’s direction, hire and mentor engineers, and collaborate with Infrastructure, Model APIs and customer teams to ship performance wins and support new model#J-18808-Ljbffr