Accelerator Compiler and Tool Chain Lead

What you'll do

• Own model ingestion, graph lowering, optimization, quantization integration, code generation, partitioning, and compiler diagnostics.
• Coordinate with runtime, driver, hardware, and firmware teams on executable formats, constraints, and performance features; establish compiler verification and regression strategy.
• Hire, mentor, and lead compiler and ML systems engineers.

What they ask for

• Deep experience developing compilers, ML graph compilers, or accelerator code generation.
• Strong understanding of ML model formats, graph IRs, operator lowering, tensor layouts, quantization, and runtime/compiler interfaces.
• Strong C++ and Python skills, with experience building production-quality compiler or systems software.
• Experience with compiler frameworks or technologies such as MLIR, LLVM, TVM, XLA, IREE, Glow, or equivalent; experience leading technical teams or major architecture areas.

Nice to have

• Experience with NPU, GPU, DSP, or AI accelerator compiler stacks and quantization-aware compilation or hardware-specific scheduling.
• Experience with model import flows, customer-facing compiler diagnostics, model-zoo validation, or open-source compiler communities.

Pay

USD 200,000–300,000 (per-year-salary) base salary

Tools

C++, Python, MLIR, LLVM, TVM, XLA, IREE, Glow

AI focus

Compiles and optimizes AI models for an NPU, including graph lowering, quantization, scheduling, and executable generation for Physical AI and other workloads.