Helix AI Engineer, Robot Learning

<h2><strong>Helix AI Engineer, Robot Learning</strong></h2> <p>Figure is an AI robotics company developing autonomous general-purpose humanoid robots. The goal of the company is to ship humanoid robots with human level intelligence. Its robots are engineered to perform a variety of tasks in the home and commercial markets. Figure is headquartered in San Jose, CA.</p> <p>We are looking for a <strong>Helix AI Engineer, Robot Learning</strong> with a strong robotics learning background to help develop and improve our <strong>visuomotor manipulation policies</strong>, with a heavy emphasis on <strong>real-robot deployment</strong>.</p> <h3><strong>Responsibilities</strong></h3> <ul> <li>Design, train, evaluate, and deploy <strong>learning-based visuomotor policies</strong> for humanoid robot manipulation</li> <li>Develop manipulation behaviors such as grasping, pick-and-place, object reorientation, door opening, bimanual manipulation, and basic assembly</li> <li>Apply and extend techniques including <strong>behavior cloning, reinforcement learning, and VLA reasoning</strong><strong><br></strong></li> <li>Train models that are robust to real-world challenges such as sensor noise, partial observability, contact dynamics, and environment variability</li> <li>Own the full pipeline from <strong>data collection on real robots</strong> to model training, evaluation, and deployment</li> <li>Work closely with simulation and digital twin tooling where useful, while prioritizing <strong>real-world performance and transfer</strong><strong><br></strong></li> <li>Collaborate with perception, controls, systems, and hardware teams to integrate policies into a full autonomy stack</li> <li>Evaluate tradeoffs between learning-based and classical approaches and make principled design decisions</li> <li>Write high-quality, well-tested software that ships to and runs reliably on physical humanoid robots</li> <li>Partner with integration and testing teams to continuously improve robustness, performance, and deployment velocity</li> </ul> <h3><strong>Requirements</strong></h3> <ul> <li>Hands-on experience developing and deploying <strong>robot learning systems on real robots</strong><strong><br></strong></li> <li>Strong background in <strong>robot manipulation and visuomotor control</strong><strong><br></strong></li> <li>Experience with <strong>behavior cloning, reinforcement learning</strong>, or related learning-based manipulation methods</li> <li>Proficiency in <strong>Python and/or C++</strong> for robotics and ML systems</li> <li>Experience with modern deep learning frameworks (e.g., PyTorch)</li> <li>Ability to design experiments, analyze failures, and iterate quickly in real-world robotic systems</li> <li>Solid understanding of the tradeoffs between classical robotics approaches and learning-based methods</li> <li>Thrive in fast-paced, ambiguous environments where solutions require exploration and ownership</li> </ul> <h3><strong>Bonus Qualifications</strong></h3> <ul> <li>Experience deploying learning-based manipulation systems in <strong>commercial or production robotic systems</strong><strong><br></strong></li> <li>Prior work on humanoids or highly dexterous robotic platforms</li> <li>Publication record in robot learning, manipulation, or embodied AI</li> <li>Experience leading projects or mentoring other engineers</li> <li>Passion for building autonomous humanoid robots that operate in the real world</li> </ul> <p>The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience. The total compensation package may also include additional components/benefits depending on the specific role. This information will be shared if an employment offer is extended.<span class="Apple-converted-space"> </span></p>