SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Hadrian is building autonomous factories to reindustrialize America by combining AI, advanced software, robotics, and full-stack manufacturing for aerospace and defense companies. The company helps customers build rockets, satellites, aircraft, ships, and mission-critical systems up to 10x faster at significantly lower cost. Following a $1.37B Series D at $7.87B valuation, Hadrian is rapidly expanding manufacturing capabilities across welding, casting, forging, electronics, additive manufacturing, and scaling its Factory-as-a-Service platform.
In this role, you will own the end-to-end data and AI/ML systems for Hadrian's additive manufacturing (AM) fleet. Your responsibilities include:
**Core Responsibilities:**
- Design and own the monitoring and analytics layer for the AM fleet, determining what is computed from raw machine and build data, what is surfaced to users, and what triggers alerts at required fidelity and traceability.
- Build and maintain curated analytical datasets, feature definitions, labeling workflows, and dataset versioning on top of the canonical machine data model.
- Develop and deploy AI/ML models trained on Hadrian manufacturing data to predict build quality, detect process anomalies, and identify parameter optimization opportunities.
- Construct feature engineering and model infrastructure including data quality checks, labeling workflows, model versioning, and production performance tracking.
- Create process monitoring dashboards and AI-driven alerting systems that give engineering and operations real-time visibility into machine and build health.
- Integrate model outputs back into OPUS and manufacturing workflows so predictions drive actionable decisions, working toward closed-loop parameter adjustment.
- Collaborate with Materials & Process and Application Engineering teams to validate model outputs against physical process knowledge before influencing production decisions.
- Apply statistical process control (SPC) to AM process data, establishing control limits and drift detection to flag machines leaving their qualified operating envelope.
- Support qualification analysis by providing capability, repeatability, and process analysis data to System Qualification Engineers and Materials & Process teams for customer data packages.
- Lead structured problem-solving on process escapes and build anomalies using 8D, 5 Whys, and fishbone analysis, driving corrective and preventive actions to verified closure.
**Requirements:**
- Bachelor's degree in Manufacturing Engineering, Computer Science, Data Science, Materials Science, or related field.
- 4+ years of experience in manufacturing data systems, process engineering, or data-driven manufacturing in a production environment.
- Hands-on experience developing and deploying AI/ML models in an engineering or manufacturing context, including model training, validation, and production deployment.
- Proficiency in Python and relevant ML frameworks (scikit-learn, TensorFlow, PyTorch, or equivalent).
- SQL fluency for working with manufacturing data at scale.
- Experience building analytical datasets from structured and time-series manufacturing data, including handling gaps, resampling, and data quality issues.
- Familiarity with structured problem-solving methodologies (8D, 5 Whys, fishbone) and statistical process control.
- Strong analytical skills with ability to connect model outputs to physical process understanding and actionable engineering decisions.
- Ability to work on site full time in Torrance, California, with up to 15% travel.
- Must be a U.S. person for ITAR purposes: U.S. citizen, lawful permanent resident, protected individual as defined by 8 U.S.C. 1324b(a)(3), or otherwise eligible to obtain required authorizations from the U.S. Department of State.
**Preferred Qualifications:**
- Experience applying AI/ML to metal additive manufacturing (build quality prediction, anomaly detection, melt pool monitoring, or process parameter optimization).
- Background with in-situ process monitoring data (layer imaging, thermal sensing, acoustic emissions, or scanner and galvanometer telemetry).
- Experience supporting qualification data packages for aerospace, defense, or regulated manufacturing environments.
- Familiarity with AMS7032, NIAR/NCAMP, or US Navy AM qualification requirements.
- MLOps practices experience (model versioning, monitoring, retraining pipelines, production deployment).
- Experience with closed-loop or feedback control of manufacturing processes using model output.
