SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 197,000 - 307,000 / annual
Agility Robotics builds Digit, the world's first commercially deployed humanoid robot already operating in real warehouses and manufacturing facilities. The company is expanding Digit's capabilities from structured work cells into open, dynamic environments where people, forklifts, and other robots move simultaneously. This shift demands dramatically improved perception systems that can reliably understand and react to unpredictable conditions while maintaining safety.
As Senior AI Software Engineer, Perception, you will own the design and implementation of perception algorithms that enable Digit to safely navigate and operate in these complex environments. Your work directly impacts human safety—every person working alongside Digit depends on your perception systems to see them, understand them, and respond correctly.
Key responsibilities include:
- Design, develop, and deploy perception algorithms (e.g., human detection) that enable safety and efficiency as Digit expands from structured cells into open, dynamic spaces
- Evaluate emerging research and state-of-the-art perception models, deciding what's worth integrating into future robot architectures
- Promote best practices in model design, implementation, and testing to deliver high-quality, scalable software
- Optimize deep neural networks and data pipelines for efficient execution on embedded systems (model structure optimization, CUDA inference, etc.)
- Establish verification and validation standards for ML-based perception models, especially for rare and safety-critical scenarios
- Collaborate across navigation, controls, and hardware teams to ensure perception serves the entire robot system
This is a hybrid role based out of one of three offices: Fremont, CA; Salem, OR; or Pittsburgh, PA.
REQUIREMENTS:
- 5+ years of experience in machine learning/perception for robotics
- Master's or Ph.D. in Artificial Intelligence, Robotics, Computer Science, or related discipline, with strong foundation in machine learning, robotics, and intelligent systems
- Demonstrated experience building ML/perception systems for safety-critical or safety-rated contexts (human detection, automotive, robotics, or comparable regulated domain)
- Deep expertise in convolutional neural networks, multi-object tracking, human detection, data association, supervised learning, and pose estimation; strong intuition for where these approaches break down in unpredictable, real-world conditions
- Experience designing and optimizing algorithms for efficient execution across CPU and GPU architectures
- Experience with MLOps, including data annotation services, data storage, model evaluation tools, and model deployment
- Publications in the field (CVPR, ICCV, RSS, ICRA preferred)
NICE TO HAVES:
- Experience designing and implementing perception systems for humanoid or legged robots
- Experience building systems with multiple sensor modalities (camera, lidar, infrared)
- Knowledge of traditional geometric computer vision and sensor hardware
