GPU Kernel Engineering Manager — Lead Inference

baseten; United States; On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Equity

Full medical, dental, vision

Flexible PTO

Parental leave

Fertility stipend

401(k)

Learning opportunities

Job summary

Baseten is seeking an Engineering Manager to lead the GPU Kernel Engineering team, a hands-on player-coach role that blends coding with people leadership. You will drive technical direction at the intersection of GPU architecture, ML systems, and production inference.

You will mentor engineers, review kernel work, and shape a roadmap that accelerates latency and cost improvements for customers relying on Baseten’s inference stack. This role requires close collaboration with senior leadership.

Qualifications

• Proven experience leading a GPU or ML systems team
• Hands-on CUDA kernel development with production experience
• Strong grasp of GPU memory hierarchy, warps and tensor cores
• Experience with NVIDIA Hopper/Blackwell architectures and the CUDA ecosystem
• Ability to set direction, roadmap, and communicate with leadership

Responsibilities

• Lead, grow, and mentor a team of GPU kernel engineers; own hiring, performance, and career development
• Set technical direction for the kernel roadmap, balancing short-term inference wins with long-term architectural investments
• Partner closely with the Chief Scientist, VP Engineering, and peer engineering leads to align kernel work with Baseten's broader inference stack strategy
• Drive cross-functional collaboration between the kernel team and Model Performance, Capacity, and Infrastructure teams
• Establish and maintain a high technical bar for kernel quality, performance, and correctness across the team's output

Skills

Team leadership

CUDA kernel development

GPU architecture

CUDA ecosystem

Technical direction

Tools

Nsight Systems

Nsight Compute

Torch Profiler

Triton

CUTLASS

CuTe DSL

Job description

Baseten is seeking an Engineering Manager to lead the GPU Kernel Engineering team, a hands-on player-coach role that blends coding with people leadership. You will drive technical direction at the intersection of GPU architecture, ML systems, and production inference.

You will mentor engineers, review kernel work, and shape a roadmap that accelerates latency and cost improvements for customers relying on Baseten’s inference stack. This role requires close collaboration with senior leadership.