Robotics Software Engineer, Mission Evaluation & Fine-Tuning

FieldAI • Irvine, CA

6d

About The Position

The Robotics Software Engineer, Mission Evaluation & Fine-Tuning owns the end-to-end inspection behavior success metric and builds the evaluation loop that supports reliable releases. This includes creating golden-labeled datasets, seeded-fault runs, and regression suites at the feature, system, and release levels to gate every release candidate.

The role turns field evidence into training and evaluation sets, connects technical performance to customer-measured metrics, and makes failures understandable. The engineer reviews mission logs, attributes misses to navigation, localization, perception, or behavior, and routes findings with supporting evidence to the responsible team.

Requirements

• Master’s degree in computer science, robotics, aerospace engineering, or a related field.
• At least 3 years of experience in robotics or ML engineering.
• Strong Python skills and working knowledge of C++.
• Comfort working with ROS 2 logs, bags, and replay tooling.
• Experience evaluating and fine-tuning vision or vision-language models, including PyTorch and LoRA or similar techniques.
• Experience building datasets and metrics for model evaluation and fine-tuning.
• Statistical rigor, including understanding the difference between benchmark results and field results and designing experiments to distinguish them.
• Data pipeline skills to move evidence from robot to training set to dashboard.

Nice To Haves

• Authored or maintained a robotics benchmark, evaluation suite, or challenge.
• Simulation-based evaluation and sim-to-real validation experience.
• MLOps experience for on-edge models, including quantization, versioning, and fleet rollout.
• Industrial inspection, gauge reading, or anomaly detection experience.

Responsibilities

• Own the end-to-end inspection behavior success metric.
• Build an evaluation loop with golden-labeled datasets, seeded-fault runs, and regression suites at feature, system, and release levels to gate every release candidate.
• Turn field evidence into training and evaluation sets.
• Map technical performance to the metrics measured by customers.
• Triage mission logs, identify whether failures stem from navigation, localization, perception, or behavior, and route them to the owning team with evidence.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level