PstrongAbout Flexion /strong /ppAt Flexion, we're building the intelligence layer powering the next generation of humanoid robots. Our mission is to accelerate the transition from fragile prototypes to real-world humanoid deployment. We are founded by leading scientists in robot reinforcement learning (ex-Nvidia, ex-ETH Zürich), and backed by leading international VC firms. In just months, we’ve gone from our first line of code to deploying real humanoid capabilities. /ppstrongThe role /strong /ppWe are seeking an expert in dexterous manipulation and large-scale modeling to lead the development of our physical foundation models. The goal of this position is to leverage internet-scale egocentric video to build Vision-Language-Action (VLA) models that enable our humanoid robots to interact with the world with human-like fluidity. You bring a deep understanding of how to bridge the gap between observing human actions in video and executing high-DOF (20+) motor control. /ppAs a Research Engineer for Dexterous Manipulation at Flexion, you’ll work in our Zürich office to develop and deploy state-of-the-art learning-based controllers. You will take ownership of the model architecture, integrating egocentric priors with real-time robot policies, to ensure our hardware can manipulate objects reliably and flexibly in unstructured environments. /ppstrongKey Responsibilities /strong /pulliScalable Egocentric Pre-training: Architect and implement large-scale pre-training objectives for egocentric video datasets to learn generalizable representations of hand-object interactions and spatial-temporal dynamics. /liliVLA Foundation Modeling: Develop and scale multi-modal Foundation Models that unify visual perception and natural language instructions into actionable robotic trajectories. /liliGenerative Policy Design: Design and optimize generative action heads using Diffusion Models and Flow-matching techniques to capture the multi-modal distribution of complex human movements. /liliHumanoid Motion Alignment: Develop novel algorithms to align human-centric video representations with the kinematic constraints of 20+ DoF humanoid systems, ensuring fluid and stable execution. /liliReinforcement Learning Fine-tuning: Utilize Offline RL and high-fidelity simulation fine-tuning to optimize foundation model performance for high-success-rate physical manipulation. /liliCross-Functional Research: Translate cutting-edge research in scaling laws and world models into production-ready architectures that enhance robot reliability and autonomy. /li /ulpstrongRequirements /strong /pulliPhD or Master’s degree in Robotics, Machine Learning, or a closely related field, with a strong focus on data-driven manipulation, egocentric vision, or foundation models. /liliExperience with Humanoid or Dexterous Manipulation, including a deep understanding of contact-rich physics. /liliExcellent knowledge of Python, PyTorch, and the distributed training of large-scale neural networks (FSDP, NCCL). /liliProven expertise in Diffusion Models, Flow Matching, and Transformers. /liliHands-on experience deploying learning-based controllers on real robot hardware. /liliExperience with Reinforcement Learning and simulation environments (e.g., IsaacLab, MuJoCo) /li /ulpstrongBenefits /strong /pulliCompetitive compensation package /liliA front-row seat at one of Europe’s most ambitious robotics companies /liliAn energetic, collaborative team with a bias for action /li /ul