Robotics Software Engineer, Mission Evaluation & Fine-Tuning

What you'll do

• Build evaluation datasets, seeded-fault runs, and regression suites to gate release candidates.
• Analyze mission logs, identify and route failures, and connect technical performance to customer metrics.
• Convert field evidence into training and evaluation sets and fine-tune vision or vision-language models.

What they ask for

• Strong Python, working C++, and comfort with ROS 2 logs, bags, and replay tooling.
• Experience evaluating and fine-tuning vision or vision-language models, including building datasets and metrics.
• Statistical rigor and data pipeline skills to move evidence from robot to training set to dashboard.

Nice to have

• Authored or maintained a robotics benchmark, evaluation suite, or challenge; simulation-based evaluation and sim-to-real validation.
• MLOps for on-edge models or experience in industrial inspection, gauge reading, or anomaly detection.

Tools

Python, C++, ROS 2, PyTorch, LoRA

AI focus

Evaluate and fine-tune vision or vision-language models for robotics inspection, using field evidence to build training and evaluation datasets.