Founding Kernel Engineer
Core
Research and build faster GPU kernels for AI workloads, focusing on inference and LLM training efficiency.
Role type
Founding Kernel Engineer (AI Compiler)
Builds
Optimized GPU kernels for AI inference and LLM training
Domain
AI Infrastructure / GPU Computing
Deliverable
production ML models
Required skills
GPU kernel development, CUDA, Triton, MLIR/LLVM, PyTorch backends, Rust, hardware performance analysis, memory hierarchies, parallel execution, benchmarking
Preferred skills
Kernel autoresearch frameworks, ML compilers, open-source compiler contributions, other accelerators
Technologies
CUDA, Triton, MLIR, LLVM, PyTorch, Rust
Responsibilities
Investigate performance bottlenecks, implement optimizations, conduct correctness checks, benchmark on real hardware, work on agent-driven systems for kernel research and automated search-based optimization
Seniority
Founding, hands-on IC
