About Humanoid

Here at Humanoid, we believe in a future where robots amplify human potential. That’s why we’ve set out on a mission to build the world’s most capable, commercially-scalable, and safe humanoid robots. We’re bringing that mission to life with HMND-01 - our rapidly developed humanoid platform being deployed in real industrial environments - and we’re growing the team to take it even further.

About the Role

We're hiring a Senior Autonomy Engineer focused on SLAM & Navigation to join our team. In this role, you will bridge the gap between classical spatial geometry and next-generation AI. You will lead the design and development of robust state estimation, long-term mapping, and localisation loops, with a specific focus on integrating modern machine learning techniques and foundation geometry models into our core navigation stack. Your work will ensure our robots possess rock-solid spatial awareness and execute highly reliable trajectories over extended deployments in complex, real-world environments.

What You'll Do

• Design and scale robust SLAM pipelines that maintain highly accurate localisation and state estimation across dynamic physical spaces.
• Integrate foundation geometry models and modern ML techniques into the localisation loop to enhance traditional spatial tracking, data association, and visual odometry.
• Architect and maintain robust long-term mapping systems that enable robots to autonomously update, manage, and scale spatial maps across changing environments over time.
• Build and scale auto-labeling data pipelines that leverage foundation geometry models to generate high-fidelity spatial ground truth for downstream ML training.
• Bridge classical geometry with deep learning architectures, building hybrid systems that map raw sensor data into globally consistent metric trajectories.
• Deploy and benchmark spatial AI software directly on physical robot hardware, ensuring deterministic, ultra-low latency execution on edge compute.
• Translate cutting-edge spatial AI research into production reality, continuously evaluating breakthroughs in geometric learning to guide our navigation roadmap.