Robotics Software Engineer, Mission Evaluation & Fine-Tuning
FieldAI
About the role
\n
What You Will Get To Do
Own the end-to-end inspection behavior success metric.
Build the evaluation loop: golden-labeled datasets, seeded-fault runs, and regression suites at feature, system, and release level that gate every release candidate.
Turn field evidence into training and evaluation sets.
Map technical performance to the metrics the customer measures.
Make failures legible: triage mission logs, attribute each miss to navigation, localization, perception, or behavior, and route it to the owning team with evidence.
What You Have
MS in computer science, robotics, aerospace engineering, or a related field, with 3+ years in robotics or ML engineering.
Strong Python, working C++, and comfort with ROS 2 logs, bags, and replay tooling.
Experience evaluating and fine-tuning vision or vision-language models (PyTorch, LoRA or similar), including building the datasets and metrics behind them.
Statistical rigor: knowing the difference between a benchmark number and a field result, and how to design an experiment that tells them apart.
Data pipeline skills to move evidence from robot to training set to dashboard.
What Will Set You Apart
Authored or maintained a robotics benchmark, evaluation suite, or challenge.
Simulation-based evaluation and sim-to-real validation.
MLOps for on-edge models: quantization, versioning, and rollout to a fleet.
Industrial inspection, gauge reading, or anomaly detection experience.
\n
Responsibilities
- Own the end-to-end inspection behavior success metric.
- Build evaluation datasets, seeded-fault runs, and regression suites to gate releases.
- Turn field evidence into training and evaluation sets.
- Connect technical performance to customer-measured metrics.
- Triage mission logs, identify failure causes, and route issues to owning teams with evidence.
Qualifications
- MS in computer science, robotics, aerospace engineering, or a related field.
- 3+ years of experience in robotics or ML engineering.
- Strong Python skills, working C++, and familiarity 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 experience designing experiments that distinguish benchmark results from field performance.
- Data pipeline skills for moving robot evidence into training sets and dashboards.
- Preferred: robotics benchmark or evaluation suite experience, simulation and sim-to-real validation, on-edge MLOps, or industrial inspection experience.
Skills mentioned
About FieldAI
FieldAI is building general robot intelligence for the physical world. FieldAI’s technology enables robots to operate safely and reliably in unstructured environments where most of the world’s work happens, without prior maps, GPS, predefined routes, or supporting infrastructure. Its hardware-agnostic approach works across different robot types, allowing customers to deploy the right form factor for the job. FieldAI robots are deployed globally across hundreds of customer sites on three continents, supporting industries including construction, energy, security, and manufacturing. Founded by veterans of NASA JPL, DARPA, and Google DeepMind, FieldAI is bringing AI off the screen and into the field.