Agility Robotics

Staff AI Engineer, Perception at Agility Robotics, focusing on designing, developing, and deploying object detection and tracking algorithms for humanoid robots. The role involves technical leadership, optimizing ML models for embedded systems, and collaborating with other engineering teams to integrate perception capabilities into production robots.

Staff Robotics Software Engineer to lead the design and development of robot behaviors, owning behavior design end-to-end from task logic to on-robot validation. The role involves working at the intersection of behavior planning, motion planning, perception, and manipulation, developing new autonomy capabilities, and integrating learned policies into hybrid workflows.

Software Engineer to develop autonomous behaviors for humanoid robots, working on algorithms, simulation, and deployment in real-world applications. Requires strong robotics fundamentals, C++, and Python.

Senior Software Engineer role focused on designing, implementing, and deploying real-time motion planning and navigation systems for humanoid robots in complex logistics and manufacturing environments. This role is critical for scaling commercial deployments and improving autonomous locomotion behaviors.

Senior Software Engineer to architect and develop core robot software, focusing on middleware, telemetry, and regression testing for autonomous behaviors in dynamic environments. Requires expertise in multi-process robot architectures, distributed systems, and simulation-to-real transitions.

Senior Robotics Software Engineer to lead the design and development of robot behaviors, expanding and generalizing humanoid robot capabilities in real-world environments. This role involves end-to-end ownership from task logic and system design to on-robot validation and deployment, working at the intersection of behavior planning, motion planning, and manipulation.

Senior Robotics Software Engineer focused on object perception for real-world robot manipulation. The role involves owning perception performance end-to-end on hardware, from sensor inputs to how outputs are consumed by downstream planners. It requires working with AI/ML engineers, exploring off-the-shelf models, classical computer vision, geometric reasoning, and learned approaches, including training or fine-tuning models.