As Lead Reinforcement Learning Engineer, you will define and execute NEURA Robotics' strategy for learning-based humanoid control. You will lead a team of reinforcement learning engineers and researchers, driving the development of next-generation locomotion, manipulation, and whole-body control capabilities for the 4NE1 humanoid platform.
You will be responsible for translating cutting-edge research into robust, production-ready systems that enable autonomous, adaptable, and commercially deployable humanoid robots. Working closely with executive leadership, product teams, controls engineers, perception specialists, and hardware teams, you will shape the future of cognitive robotics at scale.
Your mission & challenges
Define and drive the strategic roadmap for learning-based humanoid behaviors, spanning reinforcement learning, imitation learning, behavior cloning, and foundation-model-powered robotics.
Lead the development and deployment of advanced control policies for locomotion, loco-manipulation, and whole-body motion on the 4NE1 humanoid platform.
Establish scalable frameworks, processes, and quality standards for training, validating, and operating learning-based systems.
Evaluate, adapt, and industrialize state-of-the-art approaches such as reinforcement learning, imitation learning, offline learning, teleoperation, motion tracking, and robotics foundation models.
Bridge cutting-edge research and real-world applications by transforming emerging technologies into reliable customer-facing capabilities.
Spearhead sim-to-real transfer efforts through domain randomization, system identification, physics calibration, actuator modeling, and sensor alignment.
Ensure robust deployment of learned policies on physical humanoid robots with strong performance, reliability, and safety.
Build, mentor, and lead a high-performing team of reinforcement learning engineers and roboticists, fostering technical excellence and innovation.
Provide technical direction and coaching while promoting a culture of ownership, collaboration, and scientific rigor.
Work closely with Controls, Perception, Platform, Software, and Hardware teams to integrate learning-based capabilities into production robotics systems.
Align research and engineering initiatives with product goals, business priorities, and long-term company strategy.
Drive projects from early-stage research through successful deployment, establishing clear success metrics and measurable impact.
Ensure solutions are scalable, maintainable, and ready for deployment across future generations of humanoid robots.
What we can look forward to
Master's or Ph.D. in Robotics, Computer Science, Machine Learning, Artificial Intelligence, or a related field.
8+ years of experience in robotics, reinforcement learning, or machine learning, including several years in technical leadership or lead roles.
Proven track record of building and deploying learning-based robotic systems in production environments.
Demonstrated success leading multidisciplinary engineering and research teams.
Strong understanding of:
Robot dynamics and kinematics
Whole-body control
Motion planning
Sensor integration
Sim-to-real transfer methodologies
Hands-on experience with:
Isaac Lab / Isaac Sim
MuJoCo
PyTorch
ROS2
Python
C++
Ability to bridge academic research and industrial deployment.
Strategic thinker capable of shaping long-term technology roadmaps.
Outstanding stakeholder management and communication skills.
Passion for mentoring and building world-class engineering teams.
Strong ownership mindset with a proven ability to drive ambitious projects to completion.
Excellent English communication skills. German language skills are highly desirable.