Job Summary:
DensityAI is a company focused on AI accelerators, and they are seeking a Compiler Engineer specializing in MLIR. The role involves owning MLIR dialect design and collaborating with chip-design and software teams to drive the AI accelerator program.
Responsibilities:
โข Own MLIR dialect design and lowering passes for our AI accelerator โ defining the high-level tensor IR, async / streaming semantics, and sharded-tensor types that bridge ML frameworks to silicon
โข Use and develop AI-assisted tool flows to accelerate compiler development
Qualifications:
Required:
โข Exceptional abilities in MLIR dialect design, lowering pass authoring, and rewrite patterns
โข 5+ years compiler engineering experience, with hands-on MLIR contributions or equivalent IR-design experience
โข Deep understanding of tensor compilation, distributed / sharded execution, and async / streaming dataflow models
โข Strong C++ fluency and experience integrating with ML frameworks (PyTorch, JAX, ONNX, TensorFlow, or equivalent)
Preferred:
โข LLVM backend experience
โข GPU compiler experience (Triton, IREE, XLA, or equivalent)
โข open-source MLIR / LLVM contributions
Company:
DensityAI is an infrastructure for data centers serving automotive, robotics, and industrial applications Founded in 2025, the company is headquartered in Mountain View, USA, with a team of 51-200 employees. The company is currently Early Stage.