Image Processing Experts in Berlin

• Insurance service provider*

Challenge: Business-critical documents were processed through external OCR providers, with ongoing costs, dependency, and data privacy risks for sensitive insurance data.

Implementation:

• Architecture and production implementation of an on-premise OCR solution with full data ownership
• Methods for recognizing document structures as the basis for automated further processing
• ML-, NLP-, and LLM/VLM-based information extraction, especially from invoices and quotations

Success: Replaced external providers: full data ownership, GDPR-compliant processing, and 75% lower recurring OCR costs per year

Used technologies: Python, Docker, Microservices, FastAPI, PyTorch, Torchvision, MongoDB, MySQL

• Add/create test specifications
• Conduct regression tests
• Conduct release tests
• Analyze Jira tickets
• Identify software defects and fix them with C#

• Developed ASR and TSR-based speech processing pipelines on AWS, enabling efficient feature extraction and scalable deployment for speech and text analytics.
• Built a Multimodal Speech Emotion Recognition system combining NLP and deep learning (audio + text), achieving 98% accuracy and supporting real-time, cloud-based inference.
• Designed and optimized end-to-end model training and evaluation workflows using AWS services (S3, EC2, Lambda) to ensure performance, reliability, and reproducibility.
• Created and deployed interactive, user-friendly dashboards for data visualization and insight generation, supporting research teams and management in data-driven decision-making.

• Led the product development in top German FinTech within the banking and mortgages segment. A B2B SaaS full-service provider (€25M Revenue, ~400 FTEs) in the banking sector, specialized in real estate appraisals. Directed the end-to-end delivery of a customer-facing UI, robust APIs, and a mobile property inspection app. Managed cross-functional development teams (4–6 people) as well as an RPA team (2–3 people), with a focus on Customer Experience (CX), operational efficiency, and the seamless integration of B2B order and service workflows.

• Successfully implemented an AI-powered image processing system achieving 80% accuracy in image categorization, 85% in face and license plate blurring, and 75% in image deduplication, significantly enhancing automation and data integrity (GDPR and ISO 27001 standard).

• Increased product delivery efficiency by 30% by leading cross-functional teams and streamlining stakeholder communication across departments.

• Redesigned the app's frontend workflow based on user interviews, resulting in a 15% time savings per property inspection by streamlining on-site processes for field agents.

• Developed frontend automation solutions using UiPath to retrieve and store documents, significantly reducing manual workload and increasing process efficiency by 35%.

• Designed and implemented a real-time perception pipeline using YOLOv7 on Time-of-Flight (ToF) sensor data, enabling live streaming, inference, and on-frame visualization for passenger detection.
• Fine-tuned and evaluated multiple state-of-the-art monocular depth estimation models for Automatic Passenger Counting (APC), and developed a custom hybrid depth model that improved depth accuracy in challenging scene regions.
• Demonstrated that model-generated depth maps outperform raw sensor depth for APC tasks across several datasets, contributing to measurable reductions in counting error.

• Support/consulting in the development and setup of 3D photo scanner systems
• Tools used: KiCAD, ePlanP8

• Independent review and assessment of assignments in the field of image processing with neural networks and student supervision
• Assisting in the creation and annotation of an image dataset for the semantic segmentation
• Development of a demonstrator for deep learning–based liquid level detection in RGB camera images

• Conducted research and development in the field of large-scale 3D reconstruction