AI Compiler Engineer

Overview

AI Compiler Engineer to develop and optimize AI/ML graph compilers for cutting-edge workloads and efficient deployment on inference accelerators.

What you'll do

• Architect, design, and implement AI model execution optimizations on graph compilers.
• Collaborate with ML researchers and hardware/software teams to design and deploy AI models.
• Optimize neural network execution using techniques such as layer fusion and operator fusion.
• Develop compiler passes to convert high-level models (e.g., TensorFlow, PyTorch) into intermediate representations (IR).
• Implement parsing, semantic analysis, and IR generation for deep learning frameworks.
• Research and integrate advancements in compiler design, ML optimizations, and hardware acceleration.

What you'll need

• Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or a related field.
• 3+ years of compiler development focused on AI/ML graph compilers.
• Proficiency in AI graph compiler frameworks such as MLIR and Torch-FX.
• Solid background in hardware architectures (e.g., GPUs, TPUs, ASICs) and optimization techniques (fusion, quantization, tiling).
• Strong understanding of intermediate representations, code parsing, and semantic analysis.
• Proficiency in C++, Python, or other compiler-development programming languages.

Details

• Location: Remote-US, Canada, Germany and Norway.