NXP Semiconductors is seeking a Computer Vision & Robotics AI Software Engineer to join our AI software development organization in Valbonne.
In this role, you will contribute to the architecture, development, and demonstration of AI-driven Computer Vision solutions for robotics applications. You will design and implement end-to-end perception pipelines that transform camera, depth, and other sensor data into actionable robotic intelligence, enabling capabilities such as object detection, segmentation, tracking, localization, scene understanding, and autonomous navigation.
You will work as part of a multidisciplinary team across AI, embedded software, robotics, and hardware domains to rapidly translate emerging Computer Vision and Deep Learning technologies into working prototypes on real robotic platforms. A key focus of the role is the optimization and deployment of AI workloads on NXP i.MX MPU-based systems.
Your Responsibilities
- Architect, design, develop, and maintain end-to-end Computer Vision and AI perception pipelines for robotics applications.
- Prototype and demonstrate perception solutions on real robotic platforms using camera, depth, and other sensor inputs.
- Design and integrate AI-based capabilities including object detection, segmentation, tracking, localization, scene understanding, and autonomous navigation.
- Investigate, evaluate, and adapt state-of-the-art Computer Vision and Deep Learning models, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and modern vision architectures.
- Integrate AI models and perception components into embedded robotic software stacks.
- Optimize and deploy Computer Vision and AI workloads on NXP i.MX MPU-based platforms, balancing accuracy, latency, power consumption, memory usage, and computational constraints.
- Conduct hands-on experiments, benchmarking, performance analysis, and field validation on real robotic systems.
- Iteratively improve perception algorithms and system architectures based on experimental results and real-world observations.
- Develop proof-of-concept solutions demonstrating the feasibility and value of emerging AI and Computer Vision technologies for robotics.
- Participate in architecture discussions, code reviews, technical reviews, and design decisions.
- Collaborate across AI, embedded software, robotics, and hardware teams to deliver robust, scalable, and maintainable solutions.
- Document perception architectures, integration strategies, experimental results, and performance evaluations.
Your Profile
- Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Robotics, Computer Vision, or a related technical field.
- Strong knowledge of deep neural network architectures for vision, particularly:
- Convolutional Neural Networks (CNNs)
- Vision Transformers (ViTs)
- Modern object detection, segmentation, and tracking architectures
- Experience developing Computer Vision or AI perception pipelines.
- Proficiency in Python and/or C/C++ programming.
- Strong software engineering fundamentals, including software architecture, debugging, testing, and version control using Git.
- Familiarity with Linux development environments.
- Ability to evaluate and integrate AI models into larger software systems.
- Strong analytical and problem-solving skills.
- Good communication skills and ability to work effectively within multidisciplinary teams.
Academic, professional, or project experience with:
- Robotics perception and autonomous robotic systems.
- Camera-based and depth-based perception.
- Object detection, instance or semantic segmentation, object tracking, localization, or scene understanding.
- Sensor fusion and multi-sensor perception.
- Deployment and optimization of Deep Learning models on embedded or edge computing platforms.
- Model optimization techniques such as quantization and fine tuning.
- Embedded Linux development.
- Robotics middleware and software frameworks such as ROS / ROS 2.
- Computer Vision and multimedia frameworks such as OpenCV and GStreamer.
- AI inference frameworks and runtimes used for edge deployment.
- Performance profiling and optimization of AI workloads with constraints on latency, memory, compute resources, and power consumption.
- Prototyping and validation of Computer Vision algorithms on real robotic platforms.
- Research, internship, thesis, or professional experience in Computer Vision, robotics, embedded AI, or Edge AI.