Everything you need to know before applying for this role.
Berkshire Grey
Bedford, England, United Kingdom
21 September 2026
Provide technical leadership on key projectsDemonstrated experience training and adapting of existing machine learning architectures for computer vision, such as CNNs/ViTs or VLMs, to solve tasks such as grasp estimation, object detection/segmentation, depth estimation, or anomaly/outlier detectionRapidly prototype and iterate on solutions to challenging problemsWork in a fast-paced environment with changing prioritiesDemonstrated proficiency to solve real world computer vision problems with machine learningMaster’s degree in Robotics, Machine Learning, Computer Vision, Computer Science or a closely related fieldDemonstrated ability to:Experience with major deep learning frameworks such as PyTorch4+ years of experience in software development with a focus on robotic manipulation or related areasDetermine and communicate justification of technical prioritiesWork independently on a variety of projects while maintaining focusStrong verbal and written communication skills, capable of explaining complex ideas clearly and concisely to both technical and non-technical stakeholdersDevelop on and troubleshoot real robotic systemsMentor junior engineersStrong development expertise in Python and C++Experience with data science tools & libraries like numpy, pandas, scipy, matplotlib, scikit-learnMS / PhD in Machine Learning, Computer Vision, Computer Science or a closely related fieldDemonstrated technical proficiency in computer vision applied to robotic manipulation, such as grasp estimation or long-tailed object detection & segmentation in clutterExperience with:Robotic vision sensors and camera to robot calibrationBoth RGB and depth dataCollecting and training on real and synthetic datasets, including various forms of data augmentationApplying machine learning to hardware interacting with the real worldReal-time perception-based controlRobot simulators (e.g. Isaac Sim)Combining model-based and data-driven approachesDocker, cloud computing, or similar applicationsExperiment tracking and dataset management (e.g. Weights & Biases)Database systems as data source, such as MongoDBROS or ROS2Parallel/distributed systems and asynchronous/concurrent programming