Agility Robotics
Senior AI Software Engineer, Perception
$197K–$307K
Hybrid- Any Office (Fremont, CA, Salem, OR, or Pittsburgh, PA) +2 · Senior · Full-time · Posted Sep 30, 2026
- Location
- Hybrid- Any Office (Fremont, CA, Salem, OR, or Pittsburgh, PA)
Fremont, California, United States
Pittsburgh, Pennsylvania, United States - Experience
- 5+ years in machine learning/perception for robotics.
- Education
- Master's or Ph.D. in Artificial Intelligence, Robotics, Computer Science, or a related discipline.
- Visa sponsorship
- Applicants must have current authorization to work in the United States.
About the job
Design and deploy perception algorithms that help Digit detect people and hazards and operate safely in dynamic environments.
What you'll do
- Develop and deploy perception algorithms for safety and efficiency in structured and dynamic environments.
- Evaluate emerging research and optimize perception models and data pipelines for embedded systems.
- Set verification and validation standards for ML perception models and collaborate with navigation, controls, and hardware teams.
What they ask for
- Master’s or Ph.D. in Artificial Intelligence, Robotics, Computer Science, or a related discipline, with a strong foundation in machine learning, robotics, and intelligent systems.
- Experience building ML/perception systems for safety-critical or safety-rated contexts.
- Expertise in convolutional neural networks, multi-object tracking, human detection, data association, supervised learning, and pose estimation.
- Experience optimizing algorithms for CPU and GPU architectures and with MLOps.
Nice to have
- Publications in CVPR, ICCV, RSS, or ICRA.
- Experience with perception for humanoid or legged robots, multiple sensor modalities, or geometric computer vision and sensor hardware.
Pay
$197,000 — $307,000 USD (base salary)
Tools
convolutional neural networks, multi-object tracking, human detection, data association, supervised learning, pose estimation, CUDA, MLOps
AI focus
Develop safety-critical robot perception, including human and hazard detection; evaluate, optimize, verify, and validate ML models for embedded deployment.
Model-written summary · the original posting is authoritative