About the job
Agility’s commercially deployed humanoids operate alongside teams in warehouses, manufacturing facilities, and distribution centers—tackling physically demanding and repetitive tasks while enabling workers to focus on higher-value work. With industry-leading safety standards and years of proven deployment data, we're pioneering a new era of automation that enhances human potential. Agility Robotics is deploying humanoid robots that are solving real-world challenges in logistics and manufacturing. Perceiving and understanding the world is critical to Digit’s success in these applications. The Perception team is looking for a staff machine learning engineer to own the design and development of object detection and tracking algorithms.
Responsibilities
As a technical lead, you will own the architecture and technical roadmap for object perception systems used by the robot in production
Design, develop, and deploy machine learning algorithms for multi-object detection, scene understanding, and 6-DoF object pose estimation
Evaluate and drive adoption of state-of-the-art perception models
Promote best practices in architecture, design, and testing to deliver high-quality, scalable software
Optimize deep neural networks and associated data processing to run efficiently on embedded systems
Collaborate with navigation, manipulation and hardware teams to align perception capabilities with product requirements
Qualifications
Minimum
5+ years of experience deploying machine learning-based object detection algorithms on mobile robots with at least 2 years of experience in a technical leadership role
Proficiency in related technical areas such as (but not limited to) deep convolutional neural networks, multi-object tracking, data association, supervised learning and pose estimation
Strong mathematical fundamentals in linear algebra and numerical optimization and familiarity with core geometric concepts in computer vision
Familiarity with common computer vision and machine learning libraries such as (but not limited to) PyTorch, OpenCV, NumPy, etc.
Experience designing and optimizing algorithms for efficient execution across CPU and GPU architectures
Experience with MLOps such as (but not limited to) data annotation services, data storage, model evaluation tools, and model deployment
Publications in your field (CVPR, ICCV, RSS, ICRA preferred)
Preferred
Experience using YOLO, Faster/Mask R-CNN
Experience developing ML models for 3 or 6 dof pose estimation