SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
World Labs is building foundational world models that enable spatial intelligence for autonomous agents in the physical and virtual worlds. We're seeking a Research Engineer/Scientist with 6+ years of experience in robot learning, manipulation, or related areas to develop state-of-the-art robot policy methods.
In this hands-on, research-driven role, you'll work at the intersection of robotics and machine learning, collaborating closely with research scientists, ML engineers, and systems teams to translate cutting-edge robotic policies into production-ready systems.
Key responsibilities include:
- Designing and implementing modern robot learning systems, including imitation learning and reinforcement learning for manipulation
- Researching, prototyping, and productionizing robotic policies with focus on speed, precision, and scalability
- Developing and improving training pipelines for sim-to-real transfer, including domain randomization, system identification, and real-sim alignment
- Collaborating with simulation and infrastructure teams to minimize sim-to-real gap and ensure clean integration with real-robot deployment stacks
- Building end-to-end training and evaluation workflows from large-scale data generation through production deployment
- Optimizing policy performance across the stack, including training speed, inference latency, and data generation efficiency
- Diagnosing failure modes in simulation and real-world rollouts, designing principled solutions to improve robustness and generalization
- Contributing to technical direction by proposing research ideas, mentoring teammates, and establishing best practices
Required qualifications:
- 6+ years working on manipulation, locomotion, robot policy training, or related areas
- Strong foundation in robotics, neural network design, and sim-to-real transfer
- Deep experience with robot policy designs (VLA, WAM, diffusion models)
- Proficiency in Python and/or C++, with hands-on experience building research or production robotic systems
- Experience with deep learning frameworks (PyTorch) and low-level robotic controllers
- Proven ability to work in ambiguous, fast-moving environments and drive projects from concept through deployment
- Strong sense of ownership, engineering rigor, and commitment to correctness and measurable improvements
- Ability to collaborate effectively with small, high-caliber teams
You thrive on challenges, weather the storms of groundbreaking research, and are mission-driven to create spatially intelligent AI systems that empower people.
