Principal Robotics Learning Engineer

AIM•Seattle, WA

About The Position

AIM is seeking a Staff-level or more senior Robotics Learning Engineer to lead the technical development of data-driven autonomy skills for heavy equipment. This is a hands-on individual-contributor role on the technical career track, with level matched to experience and scope at Staff, Senior Staff, Principal, or above. The role involves setting technical direction and delivering learned autonomy skills using demonstrations, simulation, and machine experience, while remaining directly involved in implementation, experiments, and hardware testing. The engineer will build and evaluate a proof of concept for a representative autonomy skill, establish measurable performance baselines, identify technical gaps, and develop a phased roadmap toward deployment and continuous improvement. The work spans robot learning, data collection and training workflows, simulation, policy deployment, integration with the broader autonomy system, and reliable evaluation. Potential applications include digging, loading, grading, and interacting with variable materials. Success is measured by repeatable task performance, productivity, fewer interventions, and reliable operation across changing conditions. The position requires technical ownership of substantial robotics or robot-learning efforts, experience personally implementing and deploying learned policies on physical robots or vehicles, and depth in reinforcement learning, imitation learning, or behavior cloning. The engineer will influence decisions across robotics, controls, perception, software, and field teams; mentor engineers; and take responsibility for delivering reliable machine behavior.

Requirements

Demonstrated technical ownership at Staff level or above of substantial robotics or robot-learning efforts, including setting direction, making architecture decisions, coordinating across teams, and delivering working systems.
Track record of personally implementing, training, deploying, and evaluating learned policies on physical robots or vehicles.
Depth in reinforcement learning, imitation learning, or behavior cloning; experience across reinforcement learning and behavior cloning is welcome.
Recent hands-on contributions to production- or deployment-quality software, learning experiments, and hardware debugging, alongside technical leadership.
Experience mentoring engineers and improving technical decisions through design and code review.
Strong understanding of machine learning, optimization, and sequential decision-making, including generalization and distribution shift.
Proficiency in Python and a modern learning framework such as PyTorch or JAX.
Experience building reproducible data, training, and evaluation workflows and interpreting experimental results.
Working knowledge of robotics sufficient to reason about observations, actions, dynamics, feedback, and physical constraints.
Ability to write maintainable software, diagnose failures across system boundaries, and communicate technical tradeoffs clearly.
Degree in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, or a related field, or equivalent practical experience.

Nice To Haves

Sustained field or customer deployment of learned policies, including performance monitoring, regression prevention, and reliability improvements after launch.
Experience with demonstration collection, teleoperation, dataset design, offline reinforcement learning, policy fine-tuning, or iterative data collection.
Experience with simulation-to-reality transfer, system identification, domain randomization, or learning for contact-rich tasks.
Experience with visuomotor policies, diffusion policies, action-sequence models, or hierarchical and multitask skill learning.
C++ experience and experience integrating learned models into a robot software stack with real-time constraints.
Experience applying robot learning to off-road machines, humanoids, manipulation, locomotion, or other systems operating under variable loads and contact conditions, with the ability to transfer those methods to heavy equipment.
Hydraulic or electrohydraulic systems experience.

Responsibilities

Lead the technical effort to build and evaluate a proof of concept for a representative autonomy skill and establish a measurable performance baseline.
Use proof-of-concept findings to identify and prioritize gaps in data, simulation, learning methods, machine integration, and evaluation.
Develop and execute a phased technical roadmap from closing critical gaps through deployment and continuous improvement.
Define architecture and interfaces across data, simulation, training, policy inference, controls, and evaluation.
Choose and communicate tradeoffs among reinforcement learning, imitation learning, behavior cloning, and established robotics methods based on task needs, data availability, and measured results.
Lead cross-team execution, resolve difficult technical blockers, mentor engineers, and personally implement critical parts of the system.
Formulate robot-learning problems, including observations, actions, task goals, rewards or imitation objectives, and policy structure.
Implement and evaluate reinforcement learning, behavior cloning, or related imitation-learning approaches, combining methods when supported by evidence.
Build skills that handle variation, recover from failures, and work with existing planning and control systems.
Work with operators and robotics engineers to collect demonstrations, machine trajectories, interventions, and failure cases.
Develop tools for data synchronization, dataset curation, quality checks, versioning, and reproducible training.
Identify data gaps and design targeted collection or simulation experiments to improve coverage and robustness.
Build and improve simulation-based training and testing where useful, and characterize differences between simulated and physical behavior.
Address deployment constraints including sensor noise, latency, action limits, inference performance, and changing machine dynamics.
Integrate learned policies with perception, state estimation, controls, and runtime supervision, including fallbacks and transitions between operating modes.
Compare learned policies with appropriate baselines using held-out tasks, environments, or operating conditions.
Measure task success, intervention rate, cycle time, constraint violations, and other relevant machine outcomes.
Diagnose failures using logs and experiments, and build regression tests to catch performance losses across model and data updates.
Validate changes through simulation and controlled hardware trials before wider field deployment, working with systems and safety engineers.
Remain actively involved in writing code, training policies, debugging failures, and testing on hardware.
Raise engineering standards through design reviews, code reviews, mentorship, and clear communication of technical tradeoffs.