Senior Software Engineer, R&D

berkshiregrey; Bedford (MA); On-site; USD 120,000 - 180,000; Full time

Job summary

Berkshire Grey is seeking a Research Engineer to advance manipulation tasks in real-world robotics, spanning drivers to multi-robot orchestration in our in-house proving ground. You will contribute to state-of-the-art robot learning and data-driven policy development.

The role demands strong Python/C++ skills, ROS expertise, and a track record of prototyping through to production. Collaboration with partners and mentorship of junior engineers are key aspects of the job.

Qualifications

• Master's degree in Robotics, ML, CS, or closely related field.
• Experience in software development in robotics or automation roles.
• Strong development expertise in Python and C++.
• Experience with ROS or ROS2 and robot systems.
• Ability to work in a fast-paced environment and communicate priorities clearly.
• Experience prototyping and iterating on robot software solutions.

Responsibilities

• Contribute to training and adapting ML architectures for robot learning and visual scene understanding.
• Improve Berkshire Grey's robot policy learning data collection applications.
• Determine demonstrations, logs, sensor data, and failures suitable for fine-tuning models for new tasks or environments.
• Stay current with robotics research and evaluate applicability to BG challenges.
• Collaborate with external research partners and mentor junior engineers or interns.
• Prototype solutions quickly and create demos for stakeholders.
• Own solutions from prototype to production-ready features.

Skills

Python

C++

ROS/ROS2

Git/CI/CD

Robot systems debugging

Effective communication

Education

Master's degree in Robotics/ML/CS

Tools

PyTorch

Isaac Sim

MuJoCo

Orbit / Isaac Labs

OpenAI Gym

Docker

Cloud computing

Git

Job description

About The Job

Berkshire Grey is a leader in the field of AI and robotics, providing innovative solutions for e-commerce, retail replenishment, package handling, and logistics operations. Our technology automates complex warehouse tasks such as picking, packing, sorting, and trailer unloading.

As part of the Research & Advanced Development group, you will develop new approaches to solving a variety of challenging manipulation problems for real-world robotics systems, allowing them to understand and interact with their environment in unprecedented ways. This position offers a unique opportunity to work at the cutting edge of robotics applied to real-world challenges. Your work will span the full range of this robotics stack, from robot drivers to the multi-robot orchestration system running in Berkshire Grey's in-house robot proving ground.

Responsibilities

• Contribute to training and adapting of existing machine learning architectures for robot learning and visual scene understanding
• Contribute to the development and continuous improvement of Berkshire Grey's robot policy learning data collection application
• Determine what demonstrations, robot logs, sensor data, annotations, and failure cases are suitable for fine-tuning robot foundation models when applied to new tasks, embodiments, or environments
• Stay abreast of the latest advancements in robotics and related fields, evaluating applicability to our challenges
• Collaborate with external research partners to find solutions for BG's problem space
• Assist with mentorship of more junior engineers or interns
• Quickly prototype solutions, creating demos for stakeholders and visitors
• Own solutions from the prototype stage to robust, production-ready features
  

Minimum Qualifications

• Master's degree in Robotics, Machine Learning, Computer Vision, Computer Science or a closely related field
• Experience in software development in robotics or automation roles
• Strong development expertise in Python and C++
• Experience with modern software engineering tooling and workflows including Git and CI/CD
• Experience in working with ROS or ROS2
• Experience in designing and implementing software and algorithms for real robots, including troubleshooting of real robot systems
• Demonstrated ability to:
  • Work in a fast-paced environment with changing priorities
  • Determine and communicate justification of technical priorities
  • Rapidly prototype and iterate on solutions to challenging problems
  • Work independently on a variety of projects while maintaining focus
• Strong verbal and written communication skills, capable of explaining complex ideas clearly and concisely to both technical and non-technical stakeholders
  

Preferred Qualifications

• • 3+ years of relevant software engineering experience in robotics or automation roles
  • Demonstrated experience with one or multiple of:
    • Computer vision applied to robotic manipulation problems, such as grasp estimation, object detection/segmentation, or anomaly detection
    • Motion planning & optimization for single or bimanual manipulation
    • Imitation learning for manipulation or other real world use cases
  • Experience with:
    • Common deep learning frameworks such as PyTorch
    • Robot simulators (e.g. Isaac Sim, MuJoCo)
    • Robot learning frameworks (e.g. Orbit / Isaac Labs, OpenAI Gym)
    • Robotic sensors, such as RGB cameras and depth sensors
    • Combining model-based and data-driven approaches
    • Docker, cloud computing, or similar applications
    • Parallel/distributed systems and asynchronous/concurrent programming
    • Production robot deployment
    • Agentic coding tools
• Possessing some of these preferred qualifications is great to have but not required and should not discourage applicants from applying.
  

Travel: Occasional; up to 10%.

6110-2606JL