OpenCV Experts in Munich

• Development High-Performance ad distribution via auction
• Holistic (multi-campaign & multi-channel) advertisement placement optimization
• Algorithmic optimization for NP-Hard/NP-e
• Multiple Knapsack Problem with constraints
• Online estimation of parameters in stochastic environments

Tools: Python, R, Kotlin, MILP/SAT/CP Solvers, Pytorch, Pandas, Docker

• Architect end-to-end AI/ML solutions, with a strong focus on advanced LLM applications, autonomous agentic AI workflows using MCP toolset, vLM embedding computations, and robust agentic RAG pipelines to drive real-world business impact for clients across diverse sectors.
• Designed intelligent agentic AI workflows to automate knowledge retrieval and reasoning for B2B clients, accelerating business impact.

• Development and maintenance of IT architectures with embedded Linux systems.
• Designing, implementing, and optimizing backend applications and script-based solutions.
• Analyzing and resolving issues, including troubleshooting and user support.
• Developing and implementing security concepts for cloud solutions.
• Administering networks (DHCP, DNS, NTP, VPN).
• Technologies: Linux, PowerShell, Bash, Python, Ansible, Kubernetes, GitLab CI.
• Methods: Kanban.

Internal systems with regulatory and security requirements could not be used directly by AI tools for incident triage, troubleshooting, and documentation search. The goal was to securely integrate these systems through MCP while preserving existing acce...

• Introduced an integrated approach for structural damage detection across concrete, steel, and glass using advanced technologies such as LiDAR and thermal imaging. Highlighted cross-material interactions to enhance diagnostics and enable predictive maintenance.

• Developed an NLP-based medical note simplifier that transforms complex clinical instructions into plain, child-level English. Applied prompt engineering with Flan-T5 transformer models to extract patient-relevant actions and rephrase them into clear to-do items. Built dual Flask and Tornado backends with a printable web interface.

• Led comprehensive AI workshops for professionals, focusing on AI-driven process automation.
• Tech Stack: n8n, Make, LLMs (OpenAI, Anthropic), Prompt Engineering, Process Mapping Tools.

• Development of new simulator features and extension of existing modules using C++.

• GUI design and implementation with Qt for Windows, including redesigns to improve usability and workflow.

• Maintenance and expansion of existing codebase: refactoring, bug fixes, and modularization to support new capabilities.

• Version control using Git.

• Performance optimization of simulation to meet real-time constraints.

• Creating and maintaining documentation: technical comments, design docs, API references and user manuals.

• Led a redesign that improved operator workflow and reduced task completion time.

• Extended simulator architecture to support multiple new scenario types while preserving backward compatibility.

• Implemented refactoring and modularization that simplified maintenance and accelerated feature delivery.

• Technologies: C++03, Qt4.6, QMake, Git, V-Model, Windows

• Project: Sensor fusion application for traffic participant detection
• Software frameworks: C++ (11,14), Python, Visual Studio, MTS, Qt, GitHub, Jenkins, JIRA, Confluence, Conan, CAN, RTOS, DOORS, CMake
• Refactored and adapted sensor fusion algorithms by processing sensor data (camera and radar) for ACC and EBA as per requirements
• Handled system test issue reports in JIRA
• Tuned Kalman filters and introduced new features to enhance tracking
• Adapted architecture, detailed design (UML) and simulation tool (Qt)
• Conducted unit testing, code reviews and static code analysis in compliance with MISRA standards
• Conducted regression testing to validate software, involved in software releases (CI/CD), KPI evaluation by testing NCAP scenarios
• Flashed ADAS software to target vehicles, used UDS protocol and OBD-II tools for diagnostics and verification

• Set up the new digitization strategy.
• Using Camunda as a process engine, a new way of handling batch and dialog tasks is created.
• In close cooperation with the business department, the individual processes are created and put into production.
• Forms for controlling manual interventions, e.g. when adjusting applications, are implemented.
• Gradual migration of old code from IBM WebSphere to JBoss.
• Skills: Arquillian, Camunda, Initiative, Empathy, Hibernate, Jackson, Java/JEE, JBoss, Jersey, JSON, JUnit, Openness to criticism, Willingness to learn, REST, Teamwork, WebServices.

• Designed and implemented an advanced, agentic RAG pipeline using LangChain and LangGraph for structured data extraction from PDFs, utilizing tools, state management, and OpenAI LLMs (GPT-4) to improve accuracy and handle complex document structures.
• Developed a Google AI agent for extraction of structured information from PDF documents and deployed the agent on Vertex AI.
• Architected data pipelines using Azure Data Factory and Databricks to ingest data from Azure Blob Storage, process it with PySpark, and load it into Azure SQL Database via Linked Services.
• Containerized AI agents and services using Docker for consistent local development and deployment.
• Utilized PySpark and Dask for database querying in coordination with Azure Blob Storage and Document Storage.
• Created a ReAct agent that extracts structured data from PDF documents using tools and integrating Azure Document Intelligence.
• Contributed to the CPO invoices validation check project using Databricks to find existing CDRs and calculate total valid costs.
• Developed a conversational AI agent (chatbot) with a FastAPI backend, integrating RAG for precise tariff extraction and deployed the service using Azure Container Apps.
• Tools used: Azure, Azure OpenAI, Azure Document Intelligence, Azure Blob Storage, Google ADK, Google Cloud, Vertex AI, Gemini, Databricks, LangChain, LlamaIndex Ollama, Docker, PySpark, Azure SQL, Azure Data Factory, Azure AI Agent, Microsoft SQL Server

• Computer vision engineer responsible for development of industrial vision solutions, beginning as a working student and transitioning to a full-time role in May 2025.
• Designed and implemented vehicle detection and counting models; integrated the pipeline into a cloud-deployed system (Azure) that delivers live analytics dashboards.
• Building an offline print quality assurance system that scans corrugated-board prints on production lines to detect and classify defects such as splashes, impurities and colour deviations, deploying the solution on Jetson edge devices.
• Collaborated with cross-functional teams while focusing on computer vision components, containerization, and deployment.

• Led development and management of advanced data products and reporting solutions, driving €11M revenue in 2023. Hired and mentored a product manager to enhance product capabilities, enabling brands to gain closed-loop measurement insights.
• Defined product vision and strategy for offsite product domain globally, enabling brands to engage their most valuable customers throughout the omnichannel customer journey.
• Initiated and led data-driven martech and adtech innovations, laying groundwork for AI-powered personalization and targeted marketing across 12 countries.

• Designed and implemented multi-modal entertainment toolchains that combine passenger input, vehicle context, large-language models (text-to-text and speech-to-speech) and image generation models to deliver more interactive and immersive in-car experiences.
• Built and orchestrated tools for LLM-based agents, covering session management, background task execution, dynamic user interactions and persistent application state.
• Investigated multi-agent orchestration frameworks for in-car environments, evaluating communication protocols and architectural strategies for coordinated and reliable agent behavior.