Principal AI Compiler Engineer
At a glance
Senior ML Platform & Ops role at Nxp. Austin (Oakhill, Office) · full-time · no salary stated · we estimate $180,000–$245,000 across the United States.
Nxp has not published a salary for this role. The figure below is our estimate, not theirs.
aimlroles summary, based on the employer's posting.
What you'll do
- Build and evolve compiler tools that use AI agents to map neural networks onto NXP SoC platforms
- Create graph rewrites, scheduling, lowering and code generation methods for CPUs and custom accelerators
- Connect the compiler to frameworks such as PyTorch, TensorFlow and ONNX, and bring in new models and operations
- Improve quantization, operator fusion, memory use and layouts while tuning latency, throughput and power
- Work with hardware and software architects on compiler and accelerator design, then strengthen testing and developer support
What you bring
- An advanced degree in computer science, electrical engineering or a related area, or equivalent experience
- Substantial work building AI compilers, accelerator backends or graph optimization systems
- Strong graph and performance optimization skills for NPUs or custom accelerators
- Experience with MLIR, LLVM, TVM-like systems or another listed compiler representation, plus strong C/C++ and Python
Who this fits
This senior, hands-on role suits someone focused on AI compilers, neural-network inference and hardware-software co-design. The available locations are San Diego or San Jose, California, and Austin, Texas. Strong communication and Scrum team experience are also called for.
From the employer
Locations available: San Diego and San Jose, California or Austin, Texas
NXP is searching for a hands-on AI Compiler Engineer who thrives at the convergence of cutting-edge AI, compiler tech, and hardware design. Here, you’ll not only architect and scale a production-class AI compiler toolchain, but also rethink how AI automates, optimizes, and accelerates every step of building and deploying neural networks on NXP’s SoCs. You’ll work shoulder-to-shoulder with visionary engineers—both human and AI—enabling adaptive compilers that learn, evolve, and redefine what’s possible for embedded intelligence. With a relentless focus on hardware-software co-design, you’ll collaborate across teams to translate high-level AI models into blazing-fast, energy-efficient executables, unlocking the full potential of our silicon for real-world impact. Innovation here isn’t a catchphrase—it’s your everyday.
Job Responsibilities:
- Own the design, implementation, and evolution of an AI compiler toolchain that leverages AI agents to seamlessly map neural networks onto NXP’s SoC platforms.
- Pioneer new graph transformations, lowering, scheduling, and codegen strategies for CPUs and custom accelerators, driven by insights from AI-powered analytics.
- Build deep integrations with leading AI frameworks (PyTorch, TensorFlow, ONNX, and more), using AI agents to rapidly onboard new model architectures and ops.
- Push the envelope on quantization, operator fusion, memory planning, and layout transformations—combining human expertise and AI-guided design for state-of-the-art results.
- Partner with hardware and software architects, kernel hackers, and AI agents to co-design next-gen compiler and accelerator features, aligning silicon and code for maximum impact.
- Diagnose and crush performance bottlenecks with AI-enabled profiling and diagnostics, relentlessly tuning for latency, throughput, and power efficiency.
- Level up validation, benchmarking, and regression pipelines by harnessing AI agents—ensuring compiler correctness and world-class performance, release after release.
- Uplevel the developer experience by streamlining usability, diagnostics, and documentation—AI agents are your copilots for user support, troubleshooting, and rapid iteration.
Qualifications:
- MS/PhD (or equivalent experience) in Computer Science, EE, or related field
- Deep experience building AI compilers, accelerator backends, or graph optimization frameworks.
- Strong expertise in graph optimization and performance optimization for NPUs or custom accelerators
- Experience with MLIR, LLVM, TVM-like systems, or proprietary compiler IRs.
- Excellent C/C++ and Python skills
- Solid understanding of AI inference workloads (CNNs, transformers, perception or generative models)
- Strong communication skills are required, e.g. agile development experience in Scrum team (Product Owner or Scrum Master)
More information about NXP in the United States...
NXP is an Equal Opportunity/Affirmative Action Employer regardless of age, color, national origin, race, religion, creed, gender, sex, sexual orientation, gender identity and/or expression, marital status, status as a disabled veteran and/or veteran of the Vietnam Era or any other characteristic protected by federal, state or local law. In addition, NXP will provide reasonable accommodations for otherwise qualified disabled individuals.