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

Flexion Robotics seeks a Senior Research Engineer in Zürich to develop robust state estimation and visual odometry solutions for humanoid robots using computer vision and sensor fusion.

This position focuses on advancing the capabilities of humanoid robots by creating reliable state estimation systems. The successful candidate will leverage computer vision and sensor fusion expertise to enhance the team in Zurich, primarily utilizing proprioceptive and visual sensors to build next-generation solutions.

Responsibilities

• Design and implement robust state estimation systems tailored for humanoid robots.
• Utilize proprioceptive and visual sensors as the primary data sources for system development.

Requirements

• Demonstrated expertise in optimization-based and filtering-based state estimation and sensor fusion for robotic applications.
• Solid grasp of contemporary machine learning techniques, including sequence-to-sequence learning, autoregressive models, and diffusion models.
• Possession of a PhD or Master's degree in computer vision or robotics, accompanied by relevant professional experience.
• Several years of hands-on experience with visual inertial odometry (VIO) and motion estimation.
• Proficiency in efficient C++ programming and real-time deployment strategies.
• Practical experience with Python, PyTorch, and the training of deep neural networks.
• Direct experience working with robotic systems and/or AR/VR devices.

Nice to have

• Specialized focus on visual odometry.
• Familiarity with recent end-to-end learned odometry and motion estimation solutions.

What the company offers

• Competitive compensation package.
• Opportunity to work at one of Europe’s most ambitious robotics companies.
• Join an energetic, collaborative team with a bias for action.

About the company

Flexion Robotics is building the intelligence layer powering the next generation of humanoid robots. Founded by leading scientists in robot reinforcement learning (ex-Nvidia, ex-ETH Zürich), the company is backed by leading international VC firms. The company has gone from its first line of code to deploying real humanoid capabilities in just months, with a mission to accelerate the transition from fragile prototypes to real-world humanoid deployment.

• Building the intelligence layer powering the next generation of humanoid robots.
• Accelerating the transition from fragile prototypes to real-world humanoid deployment.
• Founded by leading scientists in robot reinforcement learning (ex-Nvidia, ex-ETH Zürich).
• Backed by leading international VC firms.
• Gone from its first line of code to deploying real humanoid capabilities in just months.