Develop ML models using in-process sensor data to identify anomalies and quality issues during printing.
Build and iterate on training and evaluation workflows; document experiments and results for reproducibility.
Own ML experimentation end to end: Design datasets, preprocessing pipelines, and training workflows; iterate on model architectures and metrics; document experiments and results for reproducibility.
Help define data collection and management: Partner with process and software teams to improve how build data is ingested, cataloged, versioned, and made available for training and evaluation.
Deploy models into production: Work with print software and embedded teams to integrate validated models into production code running on printer hardware, including performance and reliability considerations.
Collaborate with supporting software engineers: Hand off validated Python prototypes for production hardening, provide clear specifications and acceptance criteria, and support integration and regression testing.
Requirements
Bachelor's degree in Computer Science, Electrical Engineering, Applied Mathematics, or a related field; advanced degree preferred.
3+ years of experience building and evaluating machine learning models in a professional setting.
Hands-on experience with computer vision or image-based ML (e.g., segmentation, classification, or anomaly detection).
Strong Python skills and experience with modern ML frameworks (e.g., PyTorch).
Experience designing ML pipelines: data loading, preprocessing, training, evaluation, and experiment tracking.
Comfort working in a production software environment: version control, code review, testing, and cross-functional collaboration.
Ability to communicate technical tradeoffs clearly to engineers and non-engineers.
Strong programming skills in Python or C++.
Experience organizing and working with structured and unstructured datasets.
Background in a STEM or scientific discipline, with demonstrated use of ML to address substantive technical or engineering problems.
Bonus
Experience with powder bed fusion or other additive manufacturing processes.
Knowledge of manufacturing data workflows, IoT sensor data, or industrial automation systems.
Experience with image-based or time-series machine learning.
Familiarity with model deployment in production or embedded environments.
Familiarity with cloud storage and data pipelines (e.g., AWS S3, batch retrieval workflows).
Experience in domains such as robotics, aerospace, materials, instrumentation, scientific computing, or other fields where ML is applied to physical or experimental data.