Engineering Manager - Inference Performance

Baseten is a rapidly growing AI platform company that supports leading AI organizations by providing infrastructure and tools for deploying models. The company recently secured significant funding and is focused on enabling cutting-edge AI workloads. The engineering manager role is within the inference performance team, which optimizes AI model execution on GPUs to improve speed and efficiency, directly impacting customer experience and operational costs.

The manager will lead a team of inference performance engineers, focusing on GPU optimization techniques such as kernels, scheduling, batching, and caching. Responsibilities include setting technical direction, mentoring team members, and collaborating with other teams to prioritize projects. The role involves hands-on technical review, performance tuning, and ensuring the team delivers measurable improvements in model throughput and latency.

Candidates should have a background in computer science or related fields, with experience managing engineering teams and deep expertise in GPU workloads and machine learning libraries like PyTorch. The position is full-time, hybrid, and based in San Francisco or New York, with a focus on scaling the team and delivering high-performance inference solutions.