Image Processing Experts in Berlin

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

• Introduction to AI and Automation
• The Automation Project
• Make.com Foundations
• Automation Basics: Data Management
• Document Workflows, Troubleshoot, and Automate Reports
• Digression: Data as the Foundation of AI Systems
• Implementing AI Solutions in Practice
• Digression: Large Language Models (LLMs)

• Immersed myself in all aspects of sustainable construction, including planning and coordinating specialist tradespeople.
• Performed extensive hands-on work using sustainable materials and traditional craftsmanship, including clay interior finishing.
• Managed timelines, budget, and all key decisions, bearing responsibility for the consequences of any mistakes.

• Developing methods for monocular 3D facial reconstruction and personalized geometric modelling from mobile imagery
• Building learning-based approaches for facial shape estimation, video-based facial analysis, and privacy-preserving visual learning

• Creation of publications, reports, and posters (layout, infographics, image editing)
• Proofreading
• Writing and sending newsletters
• Creating forms
• Back office and support for user administration and administration for online portals
• Database and mailing list maintenance
• Dispatch campaigns for publications
• Organization of meetings, workshops, and events
• Contact person for external and press inquiries
• Assistance to management (appointment management, business trips, committee management)
• Office administration

• 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

• Marketplace audit for SEO and SEA including deriving optimization measures
• Development of a growth and optimization strategy for 2025
• Operationalization of 2025 goals into concrete actions
• Project setup in Asana and project control in weekly meetings
• 2025 budgeting for EU and US including sales and budget planning
• Setup of a weekly reporting including a plan vs. actual dashboard
• Selection of an SEA agency including requirement briefing and onboarding
• Creation of a full-cost calculation as a decision basis for FBA versus FBM

• Generated and submitted a complete patent application to the European Patent Office
• Drafted comprehensive patent applications, including detailed claim sections
• Analyzed inventions from multiple projects to identify innovative aspects
• Conducted comprehensive research on the state of the art and communicated results to stakeholders
• Collaborated with customers and various stakeholders to coordinate patent objectives and develop patent portfolios

For Regiolux GmbH, I produced several brochures and an info sheet in seven different languages in this project. To make offset printing especially efficient and cost-effective, I implemented all language variants in Adobe InDesign on separate layers. This way, the different versions could be produced by simply swapping the black printing plate—a simple but effective solution.

In addition to working according to the corporate design, my tasks also included final artwork and creating web and print PDFs. I coordinated communication with translation agencies and printers, ensuring a smooth project flow.

• 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%.

In 2024, I started my own wedding and event planning business, designing exclusive premium-segment weddings. In addition to training as a wedding and event manager, I began training as a wedding planner at the Avantgarde Academy.

• 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.

• Independently executed graphic design projects in digital and print media