10 дней назад
AI Research Scientist (Spatial AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Research Scientist (Spatial AI) (SLAM/VIO/3D Perception): Developing real-time spatial perception, visual-inertial odometry, and monocular SLAM pipelines for resource-constrained mobile edge devices with an accent on sensor fusion, 6-DoF pose estimation, and sub-centimetre AR accuracy. Focus on translating research into low-latency algorithms, optimising models for mobile NPUs, DSPs, and GPUs, and integrating on-device AI into commercial products.
Location: London, United Kingdom. Flexible hybrid model with in-person collaboration at the central London office 3 days per week and 2 days working from home.
Company
develops smart solutions for organisations, employees, and customers, with a focus on connected enterprise technologies and edge intelligence.
What you will do
- Research, design, and implement Visual-Inertial Odometry, 6-DoF camera pose estimation, and monocular SLAM pipelines for resource-constrained edge hardware.
- Develop spatial localisation, multi-view ray triangulation, IMU-camera sensor fusion, plane-fitting, and tracking algorithms targeting sub-centimetre overlay accuracy.
- Translate research papers into real-time algorithms and optimise neural networks and spatial pipelines for mobile NPUs, DSPs, and GPUs.
- Build on-device spatial foundations for augmented reality, barcode and shelf product recognition, OCR, and multimodal edge AI without cloud connectivity.
- Collaborate with global hardware, software, and product engineering teams to integrate models into commercial product roadmaps.
Requirements
- Master’s or Ph.D. in Computer Science, Robotics, Electrical Engineering, or a related quantitative field, specialising in Computer Vision, Spatial AI, or Robotics.
- At least 2 years of hands-on research and development experience with SLAM or spatial tracking systems.
- Deep theoretical and practical understanding of SLAM and Visual-Inertial Odometry.
- Strong foundation in 6-DoF pose tracking, IMU-and-vision sensor fusion, and intrinsic and extrinsic camera calibration.
- Experience with 3D geometric computer vision, including ray-plane intersections, epipolar geometry, bundle adjustment, and monocular depth estimation.
- High proficiency in C++ and/or Python and experience with machine learning and computer vision frameworks such as PyTorch, OpenCV, ROS, GTSAM, or Ceres Solver.
Culture & Benefits
- 25 days of vacation and up to 32 hours of paid annual volunteering leave.
- Training, personal development, internal learning resources, and career opportunities across Zebra departments.
- Performance-based annual cash incentive targeted at 10% of base pay, plus annual performance-related salary increases.
- Pension scheme with matched contributions of up to 7%.
- Private medical and dental cover, employee assistance programme, cycle-to-work scheme, and employee referral bonus.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →