Founding Kernel Engineer

Research and build faster kernels for AI workloads. You'll work closely with the compiler team, investigate performance bottlenecks, and take optimizations through correctness checks, benchmarking, and execution on real hardware.

San Francisco, California, United States
Full-time
On-site
$150K–$250K per year
Posted Nov 7, 2026

INDUSTRYSoftware & InternetAI & Machine Learning

Apply with RefersoAI Apply on careers page

Responsibilities

Research and build faster kernels for AI workloads
Work closely with the compiler team
Investigate performance bottlenecks
Take optimizations through correctness checks, benchmarking, and execution on real hardware
Develop agent-driven systems that write, test, and improve kernels
Automate kernel research and search-based performance optimization
Ensure more efficient execution for inference and LLM training

Requirements

Experience in a AI
Experience in a Machine Learning
Experience in a Compilers

Nice to have: kernel autoresearch frameworks, ML compilers, CUDA, Triton, GPU instruction sets, MLIR, LLVM, PyTorch backends, Rust, open-source compiler contributions, accelerators

Skills

GPU kernel developmentHardware performance analysismemory hierarchiesparallel executionbenchmarkingCUDATritonMLIRLLVMPyTorch Rust

More jobs nearby

Jobs in San Francisco, CA Jobs in California

Full description

QUALIFICATIONS - Hands-on experience developing GPU kernels. NICE TO HAVES - Prior work on kernel autoresearch frameworks is a very strong positive. - Experience with ML compilers is a strong positive, but not required. - Hardware performance analysis, memory hierarchies, parallel execution, and benchmarking. - CUDA, Triton, GPU instruction sets, or compiler systems such as MLIR/LLVM and PyTorch backends. - Rust, open-source compiler contributions, or work on other accelerators. No degree requirement. Researchers, recent PhDs, and candidates with substantial relevant projects are welcome. COMPANY Luminal (YC S25) builds an AI compiler and serving stack that optimizes models for faster, more efficient execution across accelerators. We're a small team working in person in San Francisco. ROLE Research and build faster kernels for AI workloads. You'll work closely with the compiler team, investigate performance bottlenecks, and take optimizations through correctness checks, benchmarking, and execution on real hardware. Our focus includes: - Agent-driven systems that write, test, and improve kernels. - Automated kernel research and search-based performance optimization. - More efficient execution for inference and LLM training. Candidates who require a US visa are welcome to apply. LOCATION AND COMPENSATION San Francisco, CA, US · Full-time · On-site. Annual base salary: $150,000–$250,000 USD. Equity: 0.15%–0.75%. Visa: Will sponsor.