Hands-on Engineering Manager, GPU Inference

Baseten; United States; Remote; USD 190,000 - 260,000; Full time

Job summary

Baseten is seeking an Engineering Manager to lead part of the Inference Performance team, driving faster, more efficient AI workloads on GPUs. You will manage and grow a team across inference engine and runtime, setting direction, hiring, and supporting the people doing the work.

You’ll shape how the team is structured as it scales, balance customer needs with platform investments and help bring new model architectures to production quickly.

Qualifications

• Bachelor's, Master's, or Ph.D. in CS/Engineering/Math required or related field.
• Experience leading and growing a high-performance engineering team.

Responsibilities

• Lead, mentor and grow a team of inference performance engineers through regular 1:1s and reviews.
• Hire GPU and inference talent and foster a strong collaborative team culture as it scales.
• Own the technical roadmap for runtime performance, balancing customer needs and model launches.
• Review designs, guide profiling and optimization, and reason from first principles about time and memory.

Skills

Team leadership

Mentoring

Hiring top talent

Performance optimization

GPU performance

Education

Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, Mathematics

Job description

Baseten is seeking an Engineering Manager to lead part of the Inference Performance team, driving faster, more efficient AI workloads on GPUs. You will manage and grow a team across inference engine and runtime, setting direction, hiring, and supporting the people doing the work.

You’ll shape how the team is structured as it scales, balance customer needs with platform investments and help bring new model architectures to production quickly.