Principal Compiler Engineer (AI)

TL;DR

Principal Compiler Engineer (AI Infrastructure): Leading the development of ML compiler infrastructure to optimize performance-per-watt for large-scale model inference with an accent on HW-SW co-design. Focus on lowering PyTorch/Triton workloads to machine IR and optimizing for GPUs and XPU AI hardware.

Location: Must be based in Santa Clara, New York City, or San Francisco

Salary: $120,000 - $400,000

Company

An early stage startup backed by a Tier-1 VC innovating at the chip and system level to deliver superior performance-per-watt for AI inference.

What you will do

• Lead overall compiler development efforts for the platform.
• Build and optimize ML compiler infrastructure across the entire stack.
• Lower PyTorch and Triton workloads to efficient machine IR.
• Optimize performance for GPUs (CUDA/ROCm) and XPU AI hardware.
• Collaborate on HW-SW co-design in a fast-paced startup environment.

Requirements

• PhD + 5 years of experience (or equivalent) in compilers, ML systems, or related fields.
• Proven experience developing compiler passes in LLVM or MLIR.
• Strong fundamentals in compiler design and performance optimization.
• Hands-on experience with PyTorch, Triton, and low-level code generation.
• Expertise in GPU architectures and HW-SW co-design.

Culture & Benefits

• High degree of ownership and direct impact on product development.
• Opportunity to build cutting-edge AI infrastructure from the ground up.
• Working with a team of industry veterans in a VC-backed environment.