Working Student ML Engineer

About the company

deeplify is creating an AI-first co-pilot for asset integrity in critical industrial environments. Its platform converts inspection records from infrastructure such as pipelines, chemical facilities, ships, and bridges into timely, risk-aware maintenance actions. The company combines a digital inspection product with its own deep-learning models and an evolving agentic AI system that improves through feedback from asset integrity engineers. The goal is to move asset integrity away from slow, manual, document-heavy workflows toward a more proactive, software-led, and increasingly autonomous approach.

Role overview

This working student position is for an ML engineer who wants to tackle difficult applied machine learning challenges in industrial inspection. The work spans weld defect detection, corrosion analysis on radiographic data, future ultrasonic testing-based systems, and long-range corrosion prediction. It is a practical engineering role focused on building reliable production systems from complex and messy industrial data.

Responsibilities

• Develop deep-learning solutions for identifying weld defects and analyzing corrosion in radiographic and ultrasonic inspection data.
• Coordinate and oversee external data-labeling teams.
• Run model training, evaluation, and experiment-tracking processes.
• Build and maintain production inference pipelines.
• Contribute to an exciting research initiative.

Requirements

• Strong practical experience in machine learning engineering.
• A strong sense of ownership, with the ability to take responsibility and move work forward independently.
• A fast-paced, execution-oriented mindset with the ability to create momentum.
• Comfort working on ambiguous, challenging real-world problems without an obvious solution.
• Ability to work across data handling, modeling, infrastructure, and deployment.
• Nice to have: background in computer vision, MLOps, production ML, imaging, or sensor-data systems.

Perks and benefits

• The chance to work on ambitious technical problems with real impact in industry.
• Hands-on experience building complete ML systems rather than isolated models.
• Opportunity to contribute to a scalable internal ML platform.
• Exposure to long-term technical challenges such as corrosion prediction.
• Compensation that is well above the usual range for working student roles.

Additional information

This role is a part-time onsite position in Munich, Bavaria, Germany. The role is suitable for a working student and is focused on practical delivery in a production environment.