Robotics Software Engineer III, Manipulation
Agility Robotics · Hybrid- Fremont, CA; Hybrid- Pittsburgh, PA
About this role
**Robotics Software Engineer III, Manipulation** ## About the Role 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. We’re looking for a **Robotics Software Engineer III** to join our **Skills team** and develop **manipulation behaviors** for humanoid robots. You’ll own a task vertical from definition through reliable on-robot execution, working across both **learned** and **classical** manipulation approaches. You will run our **LfD (Learning from Demonstration) flywheel** end-to-end for manipulation tasks: collecting data, defining operator instructions, improving data quality, setting up grading rubrics, training policies, evaluating failures, and iterating until the behavior is robust enough for real deployments. This role is ideal for an engineer who enjoys working close to the robot and is methodical about failure analysis—replaying logs, identifying weak points in the state distribution, root-causing failures, and building the engineering around policies and primitives so the robot can execute complete workflows. ## Key Responsibilities - Own a task vertical from definition through reliable on-robot execution - Work across learned and classical manipulation methods - Run iterative policy improvements across data collection, annotation, training, evaluation, and deployment - Work closely with teleoperators to improve data quality and operator instructions - Develop grading rubrics and evaluation workflows to measure progress (success = more reliable real-world robot policies) - Root cause failures using logs, replays, and analysis of state distributions - Integrate learned policies with higher-level skills to execute inside complete robot workflows - Build general manipulation capabilities to reduce task-specific tuning - Experiment with off-the-shelf manipulation and perception models - Partner with the ML team that owns the base large behavior model, LfD flywheel, and training recipes for post-training manipulation policies ## About You - MS or PhD in Robotics, AI, Computer Science, Machine Learning, or related field - 2+ years of experience deploying manipulation behaviors on real robots - Strong software engineering fundamentals and proficiency in **Python** - Experience with robot data collection, training, and testing on hardware for manipulation tasks - Familiarity with at least some of: grasp planning, imitation learning, reinforcement learning, force control, teleoperation, robot sensors, visual servoing, object perception - Strong analytical, experimental, and debugging skills - Comfortable working hands-on with robotic systems in a lab environment ## Location / Work Model Hybrid position based out of **Pittsburgh, PA** or **Fremont, CA** offices. ## Compensation - **Anticipated Salary Range:** **$155,000 – $241,000 USD** ## Benefits (Highlights) - 401(k) with **6% company match** - Equity (company stock options) - 100% company-paid medical, dental, vision, and short/long-term disability insurance - Benefits eligible on your first day - Employee Assistance Program (EAP) - Flexible/unlimited PTO (exempt) or paid sick leave + vacation (non-exempt), plus company holidays - Catered lunches and snacks at select locations - Generous paid parental leave - Professional development + tuition reimbursement - Relocation assistance (eligible r
Listing freshness
CronJobs last confirmed this listing 2d ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.