Applied Research Scientist in Robot Learning & Manipulation

Eurecat Technology Centre; Cerdanyola del Vallés; Hybrid; EUR 80,000 - 120,000; Full time

Job summary

Eurecat Technology Centre is seeking an Applied Research Scientist in Robot Learning and Manipulation in the Barcelona area. You will contribute to the GRAIL European flagship project, focusing on developing learning-based robotic manipulation and safe human-robot collaboration in real industrial environments.

You will work on imitation learning, reinforcement learning, and foundation models for robotics, bridging theory and real hardware through simulations and deployments with European

Qualifications

• PhD-level research maturity, either via PhD or equivalent research experience.
• Hands-on experience applying AI/ML methods to real robotic systems.
• Strong publication record and collaboration across teams.

Responsibilities

• Lead applied research and development in robot learning and manipulation.
• Develop and validate foundation models for robotics, including multimodal and vision-language-action approaches.
• Integrate AI methods on real robotic systems and in industrial settings.
• Collaborate with European partners and contribute to scientific publications and project deliverables.

Skills

Imitation learning

Reinforcement learning

Foundation models

Vision-language-action

Robotics

Human-robot collaboration

AI methods

Education

PhD-level research maturity

Tools

ROS

Python

C++

Simulation tools

Job description

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 EurecatTechnology 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) — alighthouseEuropean project to develop foundation models for robotics — and continue contributing toEurecat’srobotics 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: generativeAIischanging how robots perceive, decide, andacquirenew skills. Roboticsisnot 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 andsafehuman-robot collaboration in real industrial environments.

This is aunique opportunity to work with some of the strongest robotics and AI groups in Europe on a project that aims to shape the future ofphysicalAI 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.

Whatwill youwork on?

You will contribute to applied research and development in areas such as:

• Imitation learning, reinforcement learning, or related approaches for roboticmanipulation and mobile manipulationskill 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.