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

About Flexion: At 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. The Role: We are looking for a computer vision and sensor fusion expert to strengthen our team in Zurich. The goal of this position is to develop next-generation robust, reliable state estimation solutions for humanoid robots, primarily using proprioceptive and visual sensors. We 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. Particularly: PhD or master's degree in computer vision or robotics with relevant experience. Multi-year experience (either PhD or industry) in visual inertial odometry (VIO) and motion estimation. Excellent knowledge of efficient C++ programming and real-time deployment. Experience with Python, PyTorch, and the training of deep neural networks. Hands-on experience working with robotic systems and/or AR/VR devices. We 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. Competitive compensation Enhanced pension plan Enhanced holiday & paid leave perks Relocation & permit sponsorship Central Zürich office with top-tier robotics testing facilities and infrastructure Joining Europe's leading robotics team & exposure to never-done-before research Energetic, collaborative culture with a bias for action and regular community events