Software Engineer - GPU Kernels
Baseten · San Francisco
About this role
**Software Engineer - GPU Kernels** **About Baseten** Baseten powers mission-critical inference for leading AI companies like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. Recently raised $1.5B Series F. **The Role** Join our Model Performance team as a GPU Kernel Engineer. Design and optimize high-performance GPU kernels for state-of-the-art ML models, working on cutting-edge AI acceleration projects. **Key Responsibilities** • Design and implement high-performance GPU kernels for matrix multiplications, attention mechanisms, and mixture-of-experts routing • Write and optimize code using CUDA, PTX assembly, and architecture-specific techniques • Implement advanced features like quantization (FP8/FP4), sparsity, and compute/communication overlap • Identify and resolve performance bottlenecks using Nsight Systems, Nsight Compute, and Torch Profiler • Contribute to internal and open-source GPU libraries **Requirements** • Strong understanding of GPU architecture: memory hierarchy, thread/block/grid organization, synchronization • Proficient in C++ and GPU performance profiling tools • Knowledge of CUDA C++ API, memory access patterns, and numerical precision strategies • Familiarity with modern GPU features (tensor cores, async operations) **Nice to Have** • Experience with Transformer models and attention optimization (Flash Attention) • Familiarity with Cutlass, Triton, Thrust, or CUB • GEMM tuning and distributed/multi-GPU compute experience • Open-source GPU contributions or research publications **Benefits** • Competitive compensation with meaningful equity • 100% medical, dental, vision coverage (U.S.) • Flexible PTO + company Winter Break • Paid parental leave & fertility stipend • 401(k) facilitation (U.S.) *Equal Opportunity Employer*
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.