Senior Robotics Engineer, Robot Learning

Samsonrose | Advanced manufacturing

12h 48m ago

On-site

Full Time

United States of America

Senior Robotics Engineer, Robot Learning

Location: Los Angeles, California, United States
Employment Type: Full-Time
Department: Engineering

About the Opportunity

A fast-growing, venture-backed advanced manufacturing company is building a new model for complex manufacturing, starting with electrical wire harnesses. This organization operates its own manufacturing facilities, producing complex electrical assemblies for some of the largest aerospace and defense companies in the country. Its mission is to transform complex manufacturing through software, robotics, and automation, helping bring more production back to the U.S.

The company is looking for a Senior Robotics Engineer, Robot Learning to lead the development and deployment of learning-based manipulation capabilities across its manufacturing operations. You'll work on teaching robots to perform complex physical tasks that are difficult to automate using traditional programming alone. This includes machine tending, picking and placing parts, feeding wires, and other high-mix assembly operations where objects and tasks can vary from job to job.

What You'll Do

Own the development and implementation of learning-based robotic manipulation capabilities across production operations.
Develop learned robotic skills for tasks such as machine tending, picking, loading, feeding wires and components, and complex assembly.
Experiment with imitation learning, reinforcement learning, diffusion policies, transformer-based approaches, and other learning-based robotics methods.
Collect, process, and evaluate robot demonstrations using teleoperation, production data, and other data-collection methods.
Build and improve the data, training, and evaluation infrastructure needed to develop reliable manipulation skills.
Develop perception, grasping, and manipulation models that can operate in variable and unstructured manufacturing environments.
Investigate difficult manipulation challenges, including contact-rich tasks and deformable objects such as cables and wires.
Evaluate open-weight robot foundation models and external platforms, determining when to adopt, fine-tune, or develop models internally.
Work with the Production Robotics team to integrate learned skills into real robotic cells and production workflows.
Run rapid experiments on physical hardware, analyze failures, and iterate toward reliable production performance.
Develop clear research plans, milestones, and measurable deliverables for the robot learning program.
Evaluate emerging robotics technologies, research approaches, and potential industry partnerships.
Help hire, mentor, and develop engineers as the robot learning team grows.

What We're Looking For

Master's degree or PhD in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, or a related technical field, or equivalent hands-on experience.
Hands-on experience developing and deploying learning-based manipulation systems on real robots.
Strong understanding of robot learning approaches, including imitation learning, reinforcement learning, diffusion policies, transformer-based policies, or robot foundation models.
Experience collecting demonstrations, building datasets, and training and evaluating robotic policies using physical hardware.
Experience with perception, grasping, manipulation, and robot control.
Familiarity with contact-rich manipulation and tasks involving variable or deformable objects.
Strong programming skills in Python and C++.
Experience with PyTorch or JAX, along with robotics frameworks such as ROS2.
Ability to move quickly between research, experimentation, hardware testing, and practical deployment.
Experience evaluating model performance, identifying failure modes, and improving learned systems through iterative experimentation.
Strong ownership and problem-solving skills, with the ability to independently drive technical projects.
Excellent communication and collaboration skills, particularly when working with engineers across robotics, manufacturing, and software.
Must be a U.S. Person as defined under ITAR requirements.

Preferred Experience

Experience deploying learned robotic skills in commercial or production environments.
Background in dexterous manipulation, robotic hands, tactile sensing, or force-controlled manipulation.
Experience working with cables, wires, flexible materials, insertion tasks, or other challenging manipulation problems.
Familiarity with simulation and sim-to-real workflows using MuJoCo, NVIDIA Isaac Sim, or similar tools.
Experience evaluating or fine-tuning open-weight robot foundation models.
Research publications, open-source contributions, or demonstrated work in robot learning and manipulation.
Previous experience at a frontier robotics company, research lab, or early-stage robotics startup.
Experience building technical roadmaps, mentoring engineers, or helping establish a new engineering function.

Why This Role

This is an opportunity to work on one of the most challenging and exciting areas of robotics: teaching machines to perform complex physical tasks in real-world manufacturing environments.

Rather than focusing solely on simulations or academic research, you'll be developing learning-based systems that interact with actual production equipment and solve practical manufacturing challenges.

You'll have the freedom to experiment with emerging approaches, evaluate new models, and build the infrastructure needed to turn robot learning research into reliable production capabilities.

The company has raised over $112 million from leading venture capital investors and opened a new 80,000-square-foot manufacturing facility in Los Angeles, California, where its robotics and automation capabilities will be developed and deployed.

You'll work closely with the cofounder and Head of AI & Robotics, collaborate with a small team of senior engineers, and have meaningful influence over the technical direction of the robot learning program.

Required Skills

pythonc++pytorchjax

Required Languages

🇬🇧 English

About the Opportunity

What You'll Do

Own the development and implementation of learning-based robotic manipulation capabilities across production operations.

Develop learned robotic skills for tasks such as machine tending, picking, loading, feeding wires and components, and complex assembly.

Experiment with imitation learning, reinforcement learning, diffusion policies, transformer-based approaches, and other learning-based robotics methods.

Collect, process, and evaluate robot demonstrations using teleoperation, production data, and other data-collection methods.

Build and improve the data, training, and evaluation infrastructure needed to develop reliable manipulation skills.

Develop perception, grasping, and manipulation models that can operate in variable and unstructured manufacturing environments.

Investigate difficult manipulation challenges, including contact-rich tasks and deformable objects such as cables and wires.

Evaluate open-weight robot foundation models and external platforms, determining when to adopt, fine-tune, or develop models internally.

Work with the Production Robotics team to integrate learned skills into real robotic cells and production workflows.

Run rapid experiments on physical hardware, analyze failures, and iterate toward reliable production performance.

Develop clear research plans, milestones, and measurable deliverables for the robot learning program.

Evaluate emerging robotics technologies, research approaches, and potential industry partnerships.

Help hire, mentor, and develop engineers as the robot learning team grows.

What We're Looking For

Master's degree or PhD in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, or a related technical field, or equivalent hands-on experience.

Hands-on experience developing and deploying learning-based manipulation systems on real robots.

Strong understanding of robot learning approaches, including imitation learning, reinforcement learning, diffusion policies, transformer-based policies, or robot foundation models.

Experience collecting demonstrations, building datasets, and training and evaluating robotic policies using physical hardware.

Experience with perception, grasping, manipulation, and robot control.

Familiarity with contact-rich manipulation and tasks involving variable or deformable objects.

Strong programming skills in Python and C++.

Experience with PyTorch or JAX, along with robotics frameworks such as ROS2.

Ability to move quickly between research, experimentation, hardware testing, and practical deployment.

Experience evaluating model performance, identifying failure modes, and improving learned systems through iterative experimentation.

Strong ownership and problem-solving skills, with the ability to independently drive technical projects.

Excellent communication and collaboration skills, particularly when working with engineers across robotics, manufacturing, and software.

Must be a U.S. Person as defined under ITAR requirements.

Preferred Experience

Experience deploying learned robotic skills in commercial or production environments.

Background in dexterous manipulation, robotic hands, tactile sensing, or force-controlled manipulation.

Experience working with cables, wires, flexible materials, insertion tasks, or other challenging manipulation problems.

Familiarity with simulation and sim-to-real workflows using MuJoCo, NVIDIA Isaac Sim, or similar tools.

Experience evaluating or fine-tuning open-weight robot foundation models.

Research publications, open-source contributions, or demonstrated work in robot learning and manipulation.

Previous experience at a frontier robotics company, research lab, or early-stage robotics startup.

Experience building technical roadmaps, mentoring engineers, or helping establish a new engineering function.

Why This Role

This is an opportunity to work on one of the most challenging and exciting areas of robotics: teaching machines to perform complex physical tasks in real-world manufacturing environments.

You'll have the freedom to experiment with emerging approaches, evaluate new models, and build the infrastructure needed to turn robot learning research into reliable production capabilities.