Staff Software Engineer - GenAI Performance and Kernel

Responsibilities

• Lead the design, implementation, benchmarking, and maintenance of core compute kernels optimized for various hardware backends
• Drive the performance roadmap for kernel-level improvements including vectorization, tiling, and quantization
• Integrate kernel optimizations with higher-level ML systems
• Build and maintain profiling, instrumentation, and verification tooling
• Lead performance investigations and root-cause analysis on inference bottlenecks
• Establish coding patterns and abstractions for cross-backend portability
• Mentor and guide other engineers working on lower-level performance
• Collaborate with infrastructure and ML teams to roll out optimizations into production

Requirements

• BS/MS/PhD in Computer Science or a related field
• Deep hands-on experience writing and tuning compute kernels (CUDA, Triton, OpenCL, LLVM IR, or assembly)
• Strong knowledge of GPU/accelerator architecture including memory hierarchy and tensor cores
• Experience with advanced optimization techniques like tiling, blocking, and software pipelining
• Familiarity with ML-specific kernel libraries such as cuBLAS, cuDNN, or CUTLASS
• Strong debugging and profiling skills using tools like Nsight or NVProf
• Experience reasoning about numerical stability and mixed precision
• Track record of shipping performance-critical production software

Preferred Qualifications

• Published research in systems/ML performance venues (e.g., MLSys, ASPLOS, ISCA)
• Experience with custom accelerators or FPGA
• Experience with sparsity or model compression techniques

About the Company

Databricks is the data and AI company. More than 10,000 organizations worldwide rely on the Databricks Data Intelligence Platform to unify and democratize data, analytics and AI.