Automation Engineer

FieldAI’s Irvine team is where embodied AI meets real robots, real sensors, and real field deployments. Based in the heart of Southern California’s robotics ecosystem, we build risk-aware, reliable, field-ready AI systems that solve the hardest problems in robotics and unlock the full potential of embodied intelligence. If you want your work to ship, get tested on hardware, and improve through real deployments, Irvine is the place. We go beyond typical data-driven approaches or pure transformer-only architectures, combining rigorous engineering with learning systems proven in globally deployed solutions that deliver results today and get better every time our robots run in the field.

As an Automation Engineer at FieldAI , you will work closely with our deployed robot fleet to improve reliability and performance across real-world sites. You’ll sit at the intersection of robotics, machine learning, and field operations , owning the triage and resolution of issues across autonomy. A key part of the role is helping run our ML flywheel : identifying and prioritizing failure modes, curating and labeling data, working with modeling teams to improve models, and partnering with deployment teams to validate and ship those improvements. You’ll also have hands-on ML responsibilities, including building datasets, evaluating models, and training or fine-tuning models for new failure modes or site-specific use cases when needed. This role is ideal for someone who enjoys solving real-world problems, working across teams, and seeing their work directly improve autonomous robots in production.

. Site Performance & Failure Triage Own day-to-day triage of issues across deployed sites and identify the highest-impact failure modes. Analyze robot behavior, logs, telemetry, and model outputs to diagnose issues across perception, prediction, and planning. Track failure modes and drive issues through resolution, with a focus on consistently improving site performance. 2. ML Flywheel & Continuous Improvement Work with data/labeling, modeling, and deployment teams to turn field failures into actionable data and model improvements. Build and maintain datasets and evaluation sets for new failure modes and site-specific use cases. Measure improvements in production and ensure fixes are validated and generalized across sites. 3. Hands-on ML & Modeling Train, fine-tune, and evaluate ML models when required to address new failure modes or site-specific challenges. Experiment with data, model, and inference changes across perception, prediction, and learned planning. Help identify whether a problem is best addressed through data, labeling, modeling, or system/deployment changes. 4. Deployment & Site Support Partner with deployment and robotics engineers to integrate and validate model and system improvements on robots. Support new use cases and customer requirements from development through production deployment. Help maintain reliable operation and rapidly burn down issues across deployed sites.

Bachelor’s or Master’s degree in Computer Science, Robotics, AI, or a related field. Strong Python and experience with modern ML frameworks such as PyTorch. Experience training, fine-tuning, and evaluating machine learning models. Strong debugging and problem-solving skills, with the ability to work across ML and robotics systems. Experience with C++ and production ML/robotics systems. Understanding of ML data pipelines, labeling, evaluation, and model deployment. Interest or experience in robotics, autonomous systems, perception, prediction, or planning. Ability to work effectively across modeling, data/labeling, and deployment teams.

Experience working with real-world robotics, autonomous vehicles, or other deployed ML systems. Experience working with perception, prediction, planning, or learned navigation models. Experience diagnosing model failures and driving iterative improvements from production data.

laptop-ats-crawler v3