Founding GPU Compiler Engineer: Lead AI Compiler Stack

San Francisco Tensor Company; San Francisco (CA); On-site; USD 285,000 - 315,000; Full time

Benefits offered by this job

Relocation assistance

Bonus

Equity

Job summary

San Francisco Tensor Company is looking for a Founding GPU Compiler Engineer to be instrumental in building the core compilation infrastructure for AI workloads. This role involves designing compilation pipelines and optimizing for various GPU architectures.

Join a passionate team dedicated to redefining software efficiency and collaborate closely with ML researchers. The position is located in San Francisco and offers a competitive salary range of $285,000 - $315,000 plus benefits.

Qualifications

• Deep experience with compiler infrastructure (LLVM, MLIR, or similar).
• Strong background in GPU architecture and low-level optimization (CUDA, ROCm, or equivalent).
• Proven track record of building production‑grade compiler infrastructure.

Responsibilities

• Design and implement the main compilation pipeline from StableHLO to executable binaries.
• Develop backend code generation for multiple targets like NVIDIA and AMD.
• Work closely with ML researchers to optimize workloads.

Skills

Compiler infrastructure experience

GPU architecture knowledge

Systems programming in C++ or Rust

Tools

LLVM

MLIR

CUDA

Job description

San Francisco Tensor Company is looking for a Founding GPU Compiler Engineer to be instrumental in building the core compilation infrastructure for AI workloads. This role involves designing compilation pipelines and optimizing for various GPU architectures.

Join a passionate team dedicated to redefining software efficiency and collaborate closely with ML researchers. The position is located in San Francisco and offers a competitive salary range of $285,000 - $315,000 plus benefits.