Senior AI Software Engineer, Perception
About this role
Digit humanoid robots must transition from predictable work cells into dynamic, open facilities shared with people and forklifts, raising perception requirements so the machine reliably understands and reacts to its surroundings without failure. Agility Robotics needs a senior engineer to design and implement the algorithms that allow Digit to perceive surroundings and remain safe as deployments scale into less constrained environments. The incoming team member will own perception model architecture, optimize neural networks for embedded systems, and partner closely with navigation, controls, and hardware groups. Ideal candidates possess a strong academic foundation, extensive background in safety-critical robotics, and practical intuition for handling edge cases in unpredictable real-world spaces.
What you will do
- Design, develop, and deploy perception algorithms that enable safety and efficiency as Digit expands into open, dynamic environments.
- Evaluate emerging research and technology to drive the adoption of state-of-the-art perception models in future robot architectures.
- Promote best practices in model design, implementation, and testing to deliver high-quality, scalable software.
- Optimize deep neural networks and associated data pipelines to run efficiently on embedded systems using model structure optimization and CUDA inference.
- Establish standards for verification and validation of machine learning-based perception models for rare and safety-critical scenarios.
- Collaborate across navigation, controls, and hardware teams to ensure the perception model serves the entire robot ecosystem.
What you need
- Bring five or more years of experience in machine learning and perception for robotics.
- Hold a Master's or Ph.D. in Artificial Intelligence, Robotics, Computer Science, or a related discipline.
- Demonstrate prior experience building machine learning and perception systems for safety-critical or safety-rated contexts such as automotive or robotics.
- Possess deep expertise in convolutional neural networks, multi-object tracking, human detection, data association, supervised learning, and pose estimation.
- Show experience designing and optimizing algorithms for efficient execution across CPU and GPU architectures.
- Demonstrate experience with MLOps practices, including data annotation services, storage, evaluation tools, and model deployment.
Nice to have
- Experience designing and implementing perception systems for humanoid or legged robots specifically
- Experience building systems based on multiple sensor modalities including camera, lidar, and infrared camera
- Knowledge in traditional geometric computer vision and sensor hardware
Benefits
- 401(k) Plan with a 6% company match
- Company stock options
- 100% company-paid medical, dental, vision, and short/long-term disability insurance
- Flexible, unlimited PTO for exempt employees alongside 12 company holidays and winter shutdown
- Catered lunches four times a week with healthy snacks at Salem and Pittsburgh locations
- Professional development and tuition reimbursement programs
Skills and tech stack
Questions candidates ask
What is the remote work policy for this position?
This is a hybrid position based out of one of the company offices in Salem, Oregon, Pittsburgh, Pennsylvania, or Fremont, California. All roles are U.S.-based.
What is the salary range for the role?
The anticipated salary range is $197,000 to $307,000 USD. The final salary offered depends on factors such as market location, job-related knowledge, skills, and experience.
What kind of qualifications are required?
Candidates need five or more years of experience in machine learning or perception for robotics, plus a Master's or Ph.D. in Artificial Intelligence, Robotics, Computer Science, or a related discipline. Applicants must also have current authorization to work in the United States.
The application is on the official Agility Robotics careers page.
Apply on company site