Robotics Researcher, Manipulation

Research, develop, and implement manipulation policies for dexterous task execution

Create grasp planning and contact-rich control pipelines that are applicable to diverse objects and environments

Develop and manage data collection and teleoperation systems to support policy training on a larger scale

Train manipulation policies using various approaches such as imitation learning, reinforcement learning, or hybrid methods, and refine until they are effective in practical scenarios

Integrate manipulation with perception and autonomy pipelines

Identify and address hardware failure modes systematically

Contribute to open-source releases of manipulation research and tools.

Proficient in robotics, control theory, and motion planning

Practical experience in building and deploying manipulation systems on real robotic platforms

Skilled in Python and C++; familiarity with PyTorch or JAX

Proven track record of transitioning manipulation research from prototype to hardware deployment

Knowledge of data collection infrastructure and teleoperation for policy training

Strong debugging skills across the entire hardware-software stack

Experience with diffusion policies, transformer-based policy architectures, or large-scale foundation models for manipulation

Previous work on dexterous or in-hand manipulation

Familiarity with contact-rich or deformable object manipulation

Publications at RSS, ICRA, CoRL, or similar venues

Join a renowned research team to work on impactful projects

Take ownership of the core training code infrastructure used by the team

Engage with real models, data, and scale, rather than small-scale problems

Contribute to bridging the gap between research velocity and engineering quality

Enjoy a flexible work environment with a culture that values depth, clarity, and curiosity

PEGASI – IT Recruitment Consultancy | Email: recruit@pegasi.com.vn | Tel: +84 28 3622 8666