Machina Labs
Machine Learning Engineer
About this role
Machina Labs seeks a Machine Learning Engineer to develop and deploy ML models for robotic sheet metal forming systems. You'll transform manufacturing data into intelligence that improves precision and production speed for defense, aerospace, and mobility applications.
What you'll do
- Design, build, and train machine learning models for robotic manufacturing systems
- Deploy ML solutions into production environments
- Process and analyze raw manufacturing data to extract actionable insights
- Collaborate with engineering teams to integrate ML pipelines with robotic systems
- Optimize models for precision, speed, and adaptability in part production
- Work on scaling ML infrastructure for manufacturing applications
What they're looking for
- Machine learning model development and training
- Data preprocessing and analysis
- ML pipeline architecture and deployment
- Python or similar ML programming languages
- Experience with manufacturing or robotics data
- Scalable systems design
- Problem-solving with real-world datasets
- Production ML engineering
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Machina Labs
Machina Labs builds intelligent manufacturing software and robotic systems, particularly advanced metal forming technology called RoboForming that converts digital designs into physical production parts for aerospace, defense, and mobility industries. The company is hiring software engineers in test, robotics automation engineers, and robotic process engineers to establish quality standards, develop automation frameworks, and optimize manufacturing processes.
View all jobs at Machina LabsLikely interview questions
- Can you walk us through a time when you built an ML model for a production system? What were the biggest challenges in moving from prototype to deployment?
- How have you handled noisy or incomplete sensor data in manufacturing or robotics contexts, and what preprocessing techniques did you use?