Senior Staff AI Software Engineer, Perception
Agility Robotics · Hybrid- Any Office (Fremont, CA, Salem, OR, or Pittsburgh, PA); Remote
About this role
**Agility Robotics — Senior Staff AI Software Engineer, Perception** Agility’s commercially deployed humanoids operate alongside teams in warehouses, manufacturing facilities, and distribution centers—handling physically demanding, repetitive tasks while enabling workers to focus on higher-value work. Digit is already working in structured environments today, and the next step is expanding into open floors, shared aisles, and dynamic spaces where people, forklifts, and other robots move at the same time. That shift raises the bar for perception: Digit must reliably understand and react to an environment that’s no longer predictable or controlled. This role is about **capability and trust**—ensuring Digit can see, understand, and stay safe around every person it works near. --- ### What You’ll Do - Own the technical vision and system architecture for Perception that enables safety and efficiency, defining how Digit perceives and reasons about humans and hazards as it expands into open, dynamic environments. - Analyze key architectural tradeoffs across sensing modalities, model design, redundancy, and compute budget—balancing safety, latency, and real-world robustness. - Stay hands-on to prototype, validate, or build critical perception components. - Partner with functional safety and systems engineering to define the safety case strategy (what architecture and evidence are required). - Support failure mode and hazard analysis at the system level to shape which risks the architecture must design around. - Evaluate emerging research and decide what to adopt into future robot architectures. - Set standards for verification and validation of ML-based perception systems, especially for rare and safety-critical scenarios. - Collaborate across navigation, controls, and hardware so the perception architecture serves the whole robot. - Mentor engineers and technical leads; represent the architecture to executive leadership, partners, and customers as needed. --- ### What You Bring - 8+ years in machine learning/perception for robotics, with a track record of defining system architecture. - Master’s or Ph.D. in AI, Robotics, Computer Science, or related field; strong foundation in ML, robotics, and intelligent systems. - Experience architecting ML/perception systems for safety-critical or safety-rated contexts (e.g., human detection, functional safety, automotive/robotics, or comparable regulated domain). - Deep expertise in deep CNNs, multi-object tracking, data association, supervised learning, and pose estimation—plus strong intuition for where these approaches fail in unpredictable real-world conditions. - Experience making system-level tradeoffs across sensing modalities, redundancy, and compute constraints on embedded/real-time hardware. - Track record of setting technical direction at an organization level. - Publications are a plus (CVPR, ICCV, RSS, ICRA preferred). --- ### Nice to Haves - Experience supporting a safety case or certification submission. - Experience architecting redundant or diverse sensing systems for safety-rated perception. - Experience architecting perception systems for humanoid or legged robots. - Experience representing technical architecture to regulators, third-party certifiers, or safety auditors. - Substantial experience with FMEA, hazard analysis, and safety case strategy for autonomous/robotic systems. --- ### Location Remote role with the option to work hybrid if you’re commutable to **Salem, OR; Pi
Listing freshness
CronJobs last confirmed this listing 13h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.