Research Engineer — Robot Learning

About the role

We are hiring Research engineer in Robot Learning to design the next generation of few-shot, data-efficient imitation learning algorithms powering our robots. Your work will define how Bleu Robotics teaches robots new industrial tasks — and how fast, from how little data, and how reliably. The central research challenge is data efficiency: learning useful, generalizing behaviors from a handful of demonstrations, not thousands. Hitting our one-hour demonstration-to-deployment target depends directly on the algorithms you will design. This is a frontier research problem with immediate, measurable industrial impact: every gain in sample efficiency translates into a faster, broader, and more useful product. This is a research role focused on shipping algorithms into a real product. We are an early-stage company and do not publish at this stage. You will work in close collaboration with the Vision & Perception and Integration teams to ensure the methods you develop run on real robots, in real factories. Responsibilities • Design, prototype, and evaluate few-shot imitation learning algorithms, with a primary focus on data efficiency • Advance our internal state of the art in imitation learning, policy learning, and representation learning for control • Run rigorous experiments on real robots and contribute to the data, evaluation, and infrastructure needed to do so • Translate research prototypes into algorithms robust enough to ship as part of our product • Collaborate with the Vision & Perception and Integration teams to move research from prototype to production • Help shape the long-term research agenda of the company Required qualifications • PhD or MSc in robotics, machine learning, or a closely related field, from a leading research lab • Track record of published research at top venues such as ICRA, IROS, CoRL, NeurIPS, ICML, RSS, or equivalent • Demonstrated research expertise in imitation learning, learning from demonstration, or policy learning for robots — ideally with a focus on data efficiency or few-shot learning • Strong Python skills and fluency with PyTorch • Hands-on experience training, evaluating, and debugging learning systems on real robots (not solely simulation) • Professional proficiency in English (internal working language)