Principal Edge AI Software Engineer

NXP Semiconductors•Ottawa, ON

1d•Onsite

About The Position

Join NXP’s AI & Chip Engineering (ACE) organization—one of the company’s flagship hubs for Edge AI innovation—based in Kanata. You’ll work at the forefront of embedded AI, enabling next-generation agentic AI, generative AI, and machine learning workloads on automotive and edge platforms. Your contributions will directly power intelligent systems across automotive, robotics, and industrial applications—where real-time, reliable AI matters. This role focuses on translating advanced AI models into optimized, production-grade embedded solutions, driving performance, efficiency, and scalability on NXP silicon.

Requirements

Bachelor’s (minimum) or Master’s/PhD in Computer Science, Electrical Engineering, or related field and 10+ years of overall experience
3+ years of experience in embedded software development (C/C++, Python)
Strong experience with Linux-based embedded systems and performance-critical applications
Understanding of processor architectures (ARM, SIMD/NEON, GPU/NPU acceleration)
Experience with AI frameworks (TensorFlow, PyTorch, ONNX Runtime, LiteRT) or custom runtimes, implementing or deploying AI/ML, DSP, or computer vision algorithms
Proven track record in system-level optimization (CPU, memory, I/O, vectorization)
Strong debugging, profiling, and analytical skills

Nice To Haves

Familiarity with hardware acceleration and offload (OpenCL, CUDA, DSP toolchains)
Experience with model optimization techniques (quantization, pruning, graph optimization)
Knowledge of automotive standards (ISO 26262, Automotive SPICE, AUTOSAR, MISRA)
Exposure to Edge AI deployment pipelines and benchmarking methodologies

Responsibilities

Design, develop, and optimize high-performance Edge AI software for NXP embedded SoCs (MCU/MPU/NPU)
Enable deployment of machine learning and generative AI models, build and integrate AI runtimes, inference engines, and model pipelines for real-time execution
Drive performance optimization (latency, memory, power) through low-level system tuning
Collaborate across system, silicon, and AI teams to deliver end-to-end AI solutions
Participate in the full lifecycle: architecture → implementation → validation → production
Contribute to next-gen Edge AI frameworks and platform enablement