Research Engineer - State Estimation and Visual Odometry (ML+classic)

ph3About Flexion /h3pAt 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. /ph3The Role /h3pWe are looking for a computer vision and sensor fusion expert to strengthen our team in Zurich. /ppThe goal of this position is to develop next-generation robust, reliable state estimation solutions for humanoid robots, primarily using proprioceptive and visual sensors. /ppWe are looking for an expert in optimization-based and filtering-based state estimation and sensor fusion for robotic systems, ideally with a focus on visual odometry. Moreover, the person should have a strong understanding of modern machine learning methods, including sequence-to-sequence learning, autoregressive, and diffusion models. Good knowledge of recent end-to-end learned odometry and motion estimation solutions is beneficial. /ppParticularly: /pulliPhD or master's degree in computer vision or robotics with relevant experience. /liliMulti-year experience (either PhD or industry) in visual inertial odometry (VIO) and motion estimation. /liliExcellent knowledge of efficient C++ programming and real-time deployment. /liliExperience with Python, PyTorch, and the training of deep neural networks. /liliHands-on experience working with robotic systems and/or AR/VR devices.br/ /li /ulpWe are looking for a person who enjoys working in a team in a dynamic, fast-moving environment and is able and willing to take ownership of projects and decisions. /pulliCompetitive compensation /liliA front-row seat at one of Europe’s most ambitious robotics companies /liliAn energetic, collaborative team with a bias for action /li /ul /p #J-18808-Ljbffr