Software Engineer Compiler Front End

You will build compiler front-end pipelines that translate deep learning models into internal representations. You will develop graph optimizations, design extensible model-ingestion systems and kernel-language interfaces, establish verification mechanisms, and refine the language using real-world feedback.

Responsibilities

• Design and implement model-ingestion pipelines from deep learning frameworks into internal IR
• Develop graph-level optimizations including operator fusion, constant folding, shape inference, and layout transformations
• Build extensible ingestion structures for new model architectures and custom operators
• Design and evolve a tensor-level kernel language and user interface
• Establish verification mechanisms for translation correctness
• Collaborate to improve end-to-end compilation quality and language design

Requirements

• Bachelor's degree in Computer Science, Mathematics, or a related field
• Experience or familiarity with compilers or program transformation systems
• Understanding of PyTorch, TensorFlow, ONNX, and model representations
• Ability to create consistent user-facing programming interfaces from complex constraints
• Python proficiency and experience with Rust or C++