Senior/Staff Research Engineer - Robot Learning
Role details
Job location
Tech stack
Job description
As a Senior Research Engineer - Robot Learning, you will drive the development, adaptation, and real-world deployment of cutting-edge learning-based techniques for robotic manipulation. You will work at the intersection of machine learning, robotics, and systems engineering - scouting state-of-the-art research and translating it into robust, scalable capabilities that run on real robots every day.
You will shape the core of RobCo's robot learning stack: model selection, policy training, evaluation frameworks, and sim-to-real workflows. As a senior member of the team, you will mentor junior engineers and guide key technical decisions while keeping the stack pragmatic, efficient, and aligned with product needs.
Your Responsibilities
- Research, benchmark, and evaluate state-of-the-art robot learning methods (e.g., VLA models, transformers, diffusion policies, RL, visuomotor models)
- Adapt academic models for real-world deployment with a focus on robustness, latency, and safety
- Develop proprietary robot learning models tailored to RobCo's data, hardware, and modular platform
- Build scalable training, data, and evaluation workflows together with infrastructure and software teams
- Integrate learned policies into robotic systems including perception, control, and runtime pipelines
- Define clear performance metrics and build automated evaluation loops (simulation and hardware)
- Own benchmarking pipelines and ensure models meet deployment readiness standards
- Mentor junior engineers/researchers and lead technical reviews of learning-based components
- Collaborate closely with perception, manipulation, simulation, and software teams on system-level design
- Stay current with the state of the field and guide strategic robot learning directions at RobCo
Requirements
Do you have experience in Systems engineering?, Do you have a Master's degree?, * Advanced degree (Master's; PhD preferred) in Machine Learning, Robotics, Computer Science, or a related field
- 5-10+ years of experience in robot learning research or ML for robotics (industry or academic)
- Strong grounding in imitation learning, reinforcement learning, and simulation-to-real transfer. Publication record at conferences like CoRL, Humanoids, RSS, IROS, NeurIPS, ICLR a strong plus
- Hands-on experience deploying learned policies on real robotic systems
- Excellent Python skills; experience with PyTorch, JAX, HuggingFace, or similar frameworks
- Ability to design experiments, evaluate models rigorously, and communicate results clearly
- Proven track record mentoring engineers or researchers and driving research-quality code
- Bonus: experience with VLA/foundation models, robotic datasets, ROS 2, or scalable training systems (Ray, AWS, Slurm)