Senior Robotics Engineer (Computer Vision)

Location: Bristol, United Kingdom

Company

hirify.global develops robotics systems for manipulation, navigation, and other embodied-AI applications.

What you will do

• Develop perception systems for object detection, segmentation, tracking, pose estimation, depth, scene understanding, and task-state recognition.
• Build visual capabilities supporting grasping, manipulation, navigation, human awareness, and closed-loop robot behaviour.
• Create datasets through collection, annotation, synthetic generation, augmentation, active learning, and failure mining.
• Design offline and on-robot evaluations covering accuracy, calibration, robustness, latency, and downstream task impact.
• Integrate cameras and depth sensors, addressing calibration, synchronization, coordinate transforms, noise, and hardware-specific failures.
• Optimize and deploy perception pipelines for real-time robot compute with logging, monitoring, fallback behaviour, and regression coverage.

Requirements

• At least three years of relevant professional experience in computer vision or multimodal perception.
• Strong Python skills and substantial experience with PyTorch or an equivalent deep-learning framework.
• Knowledge of modern vision methods including detection, segmentation, tracking, pose estimation, depth, or representation learning.
• Experience building datasets, training models, selecting metrics, and performing structured error analysis.
• Understanding of camera geometry, calibration, coordinate systems, and the connection between perception outputs and physical-world decisions.
• Ability to write production-quality code and integrate models into larger software systems with testing and observability.

Nice to have

• Experience with robotic manipulation, mobile robots, autonomous systems, or embodied-AI applications.
• 6D object pose estimation, visual servoing, grasp perception, articulated-object understanding, or hand-object interaction.
• RGB-D, stereo, event-camera, LiDAR, or multi-camera systems.
• Open-vocabulary perception, vision-language models, self-supervised learning, synthetic data, simulation, or sim-to-real transfer.
• CUDA, TensorRT, ONNX, ROS/ROS 2, or deployment on embedded and edge GPU hardware.

Culture & Benefits

• Cross-functional collaboration with robot-learning, controls, simulation, hardware, and product teams.
• Work includes lab and field troubleshooting, pilot validation, and occasional travel to partner or pilot sites.
• Physical requirements include prolonged sitting or standing, computer work, and the ability to lift 30 lbs.