Engineering

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.
• Review kernel designs and implementations with enough depth to give meaningful feedback on GPU architecture decisions, memory hierarchy tradeoffs, and optimization strategies.
• Guide the team's approach to profiling and bottleneck identification using tools like Nsight Systems, Nsight Compute, and Torch Profiler.
• Stay current on the NVIDIA GPU ecosystem (Hopper, Blackwell, and beyond) and translate architectural advancements into team priorities.
• Build the processes that allow a highly technical, distributed team to ship with velocity and rigor.
• Represent the kernel team's work to senior leadership and external audiences including industry conferences.
• Contribute to Baseten's open-source GPU library presence and technical brand.

Requirements

• Proven experience leading a team of GPU or ML systems engineers, with a track record of hiring and developing strong technical talent.
• Deep personal background in GPU kernel engineering. You have written and shipped production CUDA kernels and can credibly engage with your team's work at a technical level.
• Strong understanding of GPU architecture fundamentals: memory hierarchy, warp execution, tensor cores, occupancy tradeoffs, and profiling methodology.
• Experience with NVIDIA GPU architectures (Hopper or Blackwell preferred) and the CUDA ecosystem.
• Demonstrated ability to set technical direction, prioritize a roadmap, and communicate clearly across engineering and leadership.

Nice-to-Haves

• Hands-on experience with Triton, CUTLASS, or CuTe DSL.
• Background in LLM inference kernels: attention variants, GEMMs, quantization (FP8/FP4), MoE routing.
• Open-source contributions to GPU libraries or inference frameworks.
• Experience presenting technical work at NVIDIA GTC, MLSys, or similar venues.

Benefits

• Competitive compensation, including meaningful equity.
• 100% coverage of medical, dental, and vision insurance for employee and dependents.
• Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!).
• Paid parental leave.
• Fertility and family-building stipend through Carrot.
• Company-facilitated 401(k).
• Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.