Job description

ROBOTICS RESEARCH ENGINEER San Francisco · Onsite · Full-time ABOUT BRACKET BOT We believe planet earth can thrive and be alive. Robots should manufacture goods, clean roadways, tidy our rooms, build more homes, cook healthy food, and lower the cost of living. We aren’t quite there yet, robots are too expensive, too difficult to program, fragile, and unfriendly. Bracket Bot is changing that. ABOUT THE ROLE We’re hiring a Robotics Research Engineer to develop software and machine learning for dexterous manipulation. You’ll turn research ideas into robot capabilities through experiments, model development, integration, and testing on physical hardware. This is a hands-on role based onsite in San Francisco. You’ll work with our robotics, software, and hardware engineers to make manipulation behaviors reliable beyond a single demonstration. WHAT YOU’LL DO - Develop and evaluate software and machine learning approaches for dexterous robotic manipulation. - Build data collection and evaluation workflows to measure manipulation performance and understand failures. - Implement research ideas, run experiments, and compare approaches. - Integrate learned models and manipulation behaviors into robot software. - Test on physical robots, debug failures, and improve reliability. - Document results and collaborate with software and hardware engineers to turn research into working capabilities. WHAT WE’RE LOOKING FOR - Strong programming skills and a foundation in robotics and machine learning. - Experience implementing and evaluating models or robotics algorithms. - Ability to design experiments and reason clearly about results. - Comfort debugging software on physical robots. - Clear communication and ownership from experiment through implementation. NICE TO HAVE - Experience with robotic manipulation, robot learning, imitation learning, or reinforcement learning. - Experience with robot datasets, simulation, perception, or control. - Research projects, open-source work, or deployed robot systems that demonstrate your approach. Bracket Bot is an equal opportunity employer. We’re building a diverse team and welcome applicants from all backgrounds.

Requirements

Must-haves

San Francisco · Onsite · Full-time
This is a hands-on role based onsite in San Francisco. You’ll work with our robotics, software, and hardware engineers to make manipulation behaviors reliable beyond a single demonstration.
Develop and evaluate software and machine learning approaches for dexterous robotic manipulation.
Build data collection and evaluation workflows to measure manipulation performance and understand failures.
Implement research ideas, run experiments, and compare approaches.
Integrate learned models and manipulation behaviors into robot software.
Test on physical robots, debug failures, and improve reliability.
Document results and collaborate with software and hardware engineers to turn research into working capabilities.
Strong programming skills and a foundation in robotics and machine learning.
Experience implementing and evaluating models or robotics algorithms.
Ability to design experiments and reason clearly about results.
Comfort debugging software on physical robots.
Clear communication and ownership from experiment through implementation.

Nice-to-haves

Experience with robotic manipulation, robot learning, imitation learning, or reinforcement learning.
Experience with robot datasets, simulation, perception, or control.
Research projects, open-source work, or deployed robot systems that demonstrate your approach.
Bracket Bot is an equal opportunity employer. We’re building a diverse team and welcome applicants from all backgrounds.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

machine learning

Platform: ashby
Effort: quick