Software Engineer - GPU Kernels

Baseten is an AI inference platform for deploying, optimizing, and scaling custom, open-source, and fine-tuned models in production.

San Francisco, United States
About Baseten

Baseten provides model runtimes, inference infrastructure, developer workflows, and deployment options including managed cloud, self-hosted, and hybrid environments.

View jobs by Baseten

Skills

Candidate Availability

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will design and implement high-performance GPU kernels for machine learning operations, optimize CUDA and PTX code, and apply architecture-specific techniques. You will profile bottlenecks, implement quantization and sparsity features, productionize research advances, and contribute to GPU libraries.

Requirements

  • GPU architecture
  • GPU programming
  • Memory hierarchy
  • Thread, block, and grid organization
  • Synchronization
  • Race condition mitigation
  • C++
  • GPU performance profiling
  • CUDA C++ API
  • Memory access optimization
  • Bandwidth optimization
  • Numerical precision
  • Quantization
  • Tensor core
  • Asynchronous operation
  • Transformer
  • Attention optimization
  • Flash Attention
  • Cutlass
  • Triton
  • Thrust
  • CUB
  • GEMM tuning
  • Distributed compute
  • Multi-GPU compute

Responsibilities

  • Design and implement high-performance GPU kernels for machine learning operations
  • Write and optimize code using CUDA, PTX assembly, and architecture-specific techniques
  • Apply memory coalescing, warp-level programming, tensor core acceleration, and compute/memory overlap
  • Implement quantization, sparsity, and compute/communication overlap features
  • Identify and resolve performance bottlenecks using profiling tools
  • Productionize theoretical advancements with research teams
  • Contribute to internal and open-source GPU libraries
  • Present technical contributions at industry conferences

Benefits

  • Equity
  • Medical insurance for employees and dependents in the U.S.
  • Dental insurance for employees and dependents in the U.S.
  • Vision insurance for employees and dependents in the U.S.
  • Flexible PTO
  • Company-wide Winter Break
  • Paid parental leave
  • Fertility and family-building stipend through Carrot
  • Company-facilitated 401(k) in the U.S.
Software Engineer - GPU Kernels at Baseten | JobStash