Senior Software Engineer, AI Compilers

Job Title

Senior Software Engineer, AI Compilers

Role Summary

Senior software engineer on the Kinara Group compiler team within NXP, responsible for implementing and shipping compiler and runtime components targeting an NPU for edge AI inference. The role focuses on lowering, code generation, quantization flows, performance optimization, and debugging of customer models.

Work cross-functionally with hardware architects, kernel teams, and product stakeholders to deliver production-quality compiler features used in deployed devices.

Experience Level

Senior — typically 7–8 years of software engineering experience, with substantial compiler and systems work.

Responsibilities

The role delivers production-grade compiler features and supports runtime integration, verification, and performance work:

• Implement compiler modules (MLIR dialects, lowering passes, operator fusion, target code generation) for the NPU.
• Design and deploy quantization flows and perform numerical-correctness verification.
• Develop, test, and ship stable, debuggable, and performant compiler passes and runtime integration components.
• Perform low-level optimizations and collaborate with kernel teams to close HW/SW performance gaps.
• Contribute to CI pipelines, test suites, profiling, and release processes for the compiler stack.
• Debug and root-cause performance and correctness issues on customer models and deliver reproducible fixes.
• Mentor junior engineers and participate in design reviews and cross-team coordination.
• Provide feedback to product and silicon teams on compiler-driven feature opportunities and tradeoffs.

Requirements

Required technical skills and experience for immediate impact.

• 7–8 years of software engineering experience with hands-on compiler and systems development.
• Experience with graph lowering, IR design, operator fusion, scheduling, and code generation for accelerators.
• Strong systems programming in C++; practical Python skills for tooling and infrastructure.
• Proven track record of shipping compiler components or systems software used in deployed products.
• Strong debugging and profiling skills with common performance toolchains.
• Effective cross-functional communication with hardware architects and kernel teams.
• Demonstrated ability or willingness to mentor junior engineers and improve engineering practices.

Nice-to-have:

• Familiarity with MLIR-based frontends and dialects (TOSA, StableHLO, TorchMLIR).
• Exposure to AI compiler stacks, hardware backends, or accelerator targeting.
• Experience with large-scale models or production ML inference pipelines.

Education Requirements

The posting mentions a founders' Ph.D. (founders' Ph.D. research at Stanford) in company background but does not state a required degree, field of study, certification, or "equivalent experience" language for applicants.

About the Company

Company: NXP Semiconductors

Headquarters: Nijmegen, Netherlands

NXP Semiconductors N.V. is a global semiconductor company that provides High Performance Mixed Signal and Standard Product solutions. With over 45,000 employees and operations in more than 35 countries, NXP is a leader in secure connectivity solutions for embedded applications, catering to automotive, industrial IoT, mobile, and communication infrastructure markets. The company is committed to innovation and sustainability, advancing a smarter, safer, and more sustainable world through technology.