Principal Software Engineer - Compilers

What You'll Do

• Design and develop compiler front-end architecture and model conversion frameworks .
• Build and maintain Python-based converters for ONNX , TensorFlow , and PyTorch .
• Implement graph construction , graph transformation , IR lowering , and optimization pipelines.
• Develop graph optimization passes including operator fusion , canonicalization , simplification , and decomposition .
• Design scalable pattern-matching and graph-rewrite frameworks .
• Enable support for modern AI architectures such as CNNs , Transformers , and LLMs .
• Drive validation, testing infrastructure, regression testing, and CI/CD integration.
• Debug and resolve issues across model conversion, optimization, and IR generation stages.
• Provide technical leadership , mentor engineers, and collaborate across teams.
• Required Skills & Experience 10+ years of experience in compiler development , ML systems , or AI infrastructure .
• Strong Python programming and software architecture skills.
• Deep understanding of: Intermediate Representations (IRs) Graph-based computation models Compiler transformations and optimizations Pattern matching and graph rewriting Hands-on experience with ONNX , TensorFlow , and PyTorch .
• Experience in graph parsing , graph transformations , and ML model optimizations .
• Strong understanding of CNNs , Transformers , and LLM architectures .
• Excellent debugging , problem-solving , and technical leadership skills.
• Good to Have Experience with MLIR , TOSA , StableHLO , or Torch-MLIR .
• Familiarity with AI compiler stacks such as IREE , TVM , XLA , TensorRT , or ONNX Runtime .
• Experience targeting GPUs , NPUs , DSPs , or custom AI accelerators.
• Knowledge of quantization , model optimization , and deployment workflows.
• More information about NXP in India... #LI-29f4