Applied Research Scientist in Robot Learning & Manipulation

Permanent position | Robotics & AI | GRAIL European flagship project | Barcelona area | Hybrid work Are you excited about building the next generation of robots that can learn, adapt, and act in the physical world? The Robotics and Automation Unit at Eurecat Technology Centre is looking for an Applied Research Scientist in Robot Learning and Manipulation. This is a permanent research position. You will work on GRAIL (Grant Agreement No. 101298421) - a lighthouse European project to develop foundation models for robotics - and continue contributing to Eurecat's robotics roadmap beyond the project. GRAIL is aligned with the European push to develop trustworthy generative AI and foundation models for robotics, including real-world validation on robotic hardware and industrial use cases. We are looking for someone with PhD-level research maturity - either through a completed PhD or equivalent research experience - and hands-on experience applying AI/ML methods to real robotic systems. Why this role matters? Robotics is entering a new phase: generative AI is changing how robots perceive, decide, and acquire new skills. Robotics is not just about language. Robots must deal with contact, uncertainty, limited data, hardware constraints, safety, and the messy complexity of the physical world. In this role, you will help bridge that gap: turning advanced AI methods into robust robotic capabilities for manipulation and safe human-robot collaboration in real industrial environments. This is a unique opportunity to work with some of the strongest robotics and AI groups in Europe on a project that aims to shape the future of physical AI and industrial automation. If you want your research to move beyond papers and benchmarks into real robotic systems, this is the kind of opportunity you should not miss. What will you work on? You will contribute to applied research and development in areas such as:

• Imitation learning, reinforcement learning, or related approaches for robotic manipulation and mobile manipulation skill acquisition.

• Foundation models for robotics, including multimodal and vision-language-action approaches, that can generalise across tasks, objects, environments, or robotic platforms.

• Integration and validation of AI methods on real robotic systems.

• Human-robot collaboration and manipulation in industrial or semi-structured environments.

• Scientific publications, project deliverables, demonstrations, and collaboration with European partners.

You will work on both simulations and real-world robotic systems, going beyond isolated academic benchmarks. The role focuses on developing innovative ideas, implementing them, testing them on real robots, and refining them to meet practical constraints.

We do not expect you to match every keyword. We are looking for depth, curiosity, and the ability to turn research ideas into working robotic systems. Essential

• PhD in Robotics, Artificial Intelligence, Machine Learning, Computer Vision, Control, or a related field; or equivalent research experience.

• Strong background in machine learning or deep learning applied to robotics.

• Experience with robot learning, manipulation, embodied AI, learning for control, or AI-based robotic perception/action.

• Strong programming skills in Python.

• Ability to work with real robotic systems, not only offline datasets or simulation.

• Scientific and technical maturity: ability to define problems, test hypotheses, analyse results, and communicate findings.

• Good written and spoken English.

Highly valuable

• Experience with imitation learning, behaviour cloning, reinforcement learning, offline RL, diffusion policies, transformers, VLA models, or foundation models for robotics.

• Experience with ROS/ROS 2.

• Experience with PyTorch, TensorFlow, or similar frameworks.

• Experience with robotic arms, mobile manipulators, force/contact-rich manipulation, bimanual manipulation, or human-robot collaboration.

• Publications, open-source contributions, project demos, or research prototypes in robot learning or embodied AI.

• Experience in European or collaborative R&D projects.

This role is probably a good fit if…

• You have worked on AI methods that make robots perceive, decide, manipulate, adapt, or learn.

• You enjoy both research and implementation.

• You are comfortable moving between papers, code, experiments, robots, and project discussions.

• You want to work in applied research: scientifically ambitious, but connected to real systems and industrial impact.

• You are attracted by the opportunity to contribute to a European flagship effort in robotics foundation models.

This role is probably not the best fit if your main experience is limited to…

• Generic object detection without a connection to robot action or manipulation.

• LLM chatbot development without robotics.

• Pure navigation, PLC programming, or classical control with no AI/robot-learning component.

• Simulation-only research with no interest in deploying on real robots.

• Software front-end or general AI engineering unrelated to physical robotic systems.

What Eurecat offers Eurecat is a leading technology centre in Catalonia, working at the intersection of research, technology transfer, and industrial innovation. In our Robotics and Automation Unit, we develop applied research in service and industrial robotics, including manipulation, human-robot collaboration, perception, cognition, robot behaviour, and autonomous systems. You will join a team with strong expertise in European projects, industrial collaborations, and real-world robotic demonstrators. Our laboratory is based in Cerdanyola del Vallès, just outside Barcelona, at the heart of a vibrant and growing robotics and AI ecosystem that brings together leading research centers, universities, technology companies, and innovation initiatives. Additionally, you will have these conditions and benefits:

• Permanent contract.

• Hybrid work.

• Flexible schedule.

• Shorter workday on Fridays and summer schedule.

• Flexible compensation package: health insurance, transport, lunch vouchers, training, kindergarten, and other benefits.

• Access to Eurecat Academy courses.

• Language training in English, Catalan, and Spanish.

• Participation in a major European robotics and AI project with leading academic and industrial partners.

• The opportunity to build long-term research lines beyond a single project.

Eurecat is the second Research & Technology Organisation in Spain and one of the largest applied research and technology transfer organisation in Southern Europe. It brings together the experience of more than 800 professionals who generate an annual turnover of 69 million euros and provides services to more than 2,000 companies. Eurecat integrates advanced digital capabilities and experience in biotechnology, industry and sustainability and collaborates with industry in R+D+I activities and projects, offering advanced scientific and technological services and specialized knowledge to respond effectively to the technological needs of very different business sectors, accelerating innovation, reducing both risks and spendings on scientific and technological infrastructures. The technology center participates in more than 200 large national and international consortium projects of high strategic R&I, has 230 patents and 10 spin-offs. Eurecat has eleven centers in Catalonia and presence in Madrid, Malaga and Chile.