Senior Applied AI/ML and Software Engineer

Applied Machine Learning and AI Engineer with a focus on building production-ready deep learning systems. Experience spans model development, data analysis, and integration of ML components into larger software ecosystems, including regulated environments like medical software (IVDR CE).

Main interest lies in end-to-end machine learning systems: from data pipelines and model training to deployment, monitoring, and long-term maintainability. Strong emphasis on translating research ideas into robust implementations that operate under real-world constraints, particularly in high-resolution computer vision and multi-task learning settings.

Key skills: Designing Deep Learning models in with , and deployment using .

• Transformer-based and convolutional architectures for computer vision
• Instance segmentation, detection, and spatiotemporal modeling
• Multi-task learning and representation learning under limited supervision
• MLOps workflows for reproducible training and deployment pipelines
• Containerized ML systems and service-oriented architectures
• Data engineering for large-scale imaging and structured datasets
• Model serving, optimization, and inference efficiency in production
• Integration of ML systems into backend and clinical software environments
• NLP/LLMs using Langchain
• API and backend development for ML systems (FastAPI/Django, RESTful service design)

• Leading interdisciplinary AI and software engineering teams
• Translating research concepts into production-ready systems
• Stakeholder communication across engineering, clinical, and research domains
• Agile project coordination and technical mentoring
• Strong focus on pragmatic problem solving and maintainable system design

CellViT / CellViT++ Transformer-based deep learning architectures for instance segmentation and classification in high-resolution image data. Focus on scalable inference, architectural efficiency, and deployment-oriented design patterns. Work includes adaptation of modern foundation-model concepts to dense prediction tasks. More than 500 ⭐'s

Development of AI-integrated software systems for digital pathology workflows, including integration of machine learning modules into laboratory information systems and clinical backend architectures. Focus on interoperability, deployment reliability, and software engineering under regulatory constraints (MDR/IVDR and EU AI Act context).

Peer-reviewed contributions in machine learning and medical imaging in digital pathology and radiology: Full list: https://scholar.google.de/citations?user=FFNSvqkAAAAJ&hl=de&oi=ao