Automation Engineer (Forward Deployment)
Confirmed on the employer's own hiring board on Oct 23, 2026. First seen by Alion on Sep 25, 2026. FieldAI scores A on the Alion truth index.
About This Role
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.
What You’ll Get To Do
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.
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.
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.
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.
. Site Performance & Failure Triage
2. ML Flywheel & Continuous Improvement
3. Hands-on ML & Modeling
4. Deployment & Site Support
What You Have
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.
What Sets you Apart
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.