Senior Engineer, AI Systems

What you'll do

• Design, implement, and optimize high-performance Triton kernels for LLM workloads on accelerators.
• Analyze kernel performance using profiling tools to identify memory access patterns and synchronization issues.
• Propose concrete optimizations to address performance bottlenecks in kernel design.
• Work with hardware architects and compiler engineers to co-design solutions spanning software and hardware boundaries.
• Prototype and evaluate kernel optimizations using experimental domain-specific languages (DSLs) and compiler flows.

What we're looking for

• Strong experience writing high-performance Triton kernels for GPUs or other accelerators.
• Solid understanding of large language model fundamentals and transformer architectures.
• Deep knowledge of accelerator hardware architecture, including memory hierarchies.
• Proven ability to read and interpret profiling data and performance counters.
• Experience diagnosing and resolving performance bottlenecks in kernel-level code.
• Strong systems programming skills in Python and low-level performance-oriented paradigms.
• Familiarity with emerging domain-specific languages (DSLs) for accelerator programming.