remote
AI/ML Compiler Engineer - NXP Semiconductors
Software Engineer
Lead the design and implementation of AI/ML compiler technologies, optimizing models for embedded hardware using C++ and LLVM to deliver high‑performance inference across diverse semiconductor platforms.
About the role
Key Responsibilities
- Design, develop, and maintain AI/ML compiler pipelines that translate high‑level models into efficient, hardware‑targeted code.
- Collaborate with hardware and software teams to optimize performance, memory usage, and power consumption on embedded processors.
- Implement advanced optimization passes, code generation, and profiling tools within the LLVM framework.
- Integrate new AI/ML frameworks (e.g., TensorFlow, PyTorch) and support emerging model formats.
- Provide technical guidance, code reviews, and mentorship to junior engineers.
Requirements
- Strong background in compiler theory, C++ programming, and experience with LLVM or similar toolchains.
- Hands‑on experience with AI/ML model optimization and deployment on embedded or low‑power devices.
- Knowledge of hardware architecture, instruction set design, and performance profiling.
- Excellent problem‑solving skills and ability to work in a fast‑paced, cross‑functional environment.