Data Science Expert in Germany

• Investigate the relationship between Eddy Current Testing (ECT) signals and microstructural properties
• Detect latent patterns in ECT data that reflect intrinsic material characteristics
• Develop and validate predictive models for microstructural classification and quantification, using hardness and case depth as benchmarks
• Apply Bayesian Structural Equation Modeling for advanced data analysis

• Designed and developed a production-ready data platform based on Microsoft Fabric for an e-commerce company
• Built a scalable Medallion Architecture (Bronze, Silver, Gold) with Lakehouse and Delta Lake as the foundation for analytics and AI applications
• Developed a metadata-driven ETL platform with PySpark and a generic Incremental Loading Framework (SQL Server → Bronze → Silver → Gold)
• Developed reusable components for Microsoft Fabric Notebooks to standardize data integration, transformation, and validation
• Implemented automated data pipelines including monitoring, logging, error handling, and Delta MERGE strategies for stable production operations
• Built a business layer architecture for reporting, data warehousing, and reusable data products
• Integrated heterogeneous data sources via SQL Server, REST APIs, Amazon SP API, and Google Analytics 4
• Worked closely with business departments to analyze business requirements and translate them into scalable data architectures

Technologies: Microsoft Fabric, PySpark, Python, SQL Server, Delta Lake, Lakehouse, OneLake, Data Factory, Data Warehouse, REST APIs, Amazon SP-API, Google Analytics 4

Development of AI and traditional models to analyze medical and patient data, including medication analyses, diagnosis analyses, forecasts, procedure analyses, dosage analyses, comorbidity analyses, prescription analyses, patient potential analyses, referral profile analyses, and prescription analyses. Analyses in the field of Real World Evidence.

Healthcare IT, pharmaceutical industry

Tasks, responsibilities:

• Gathering customer requirements
• Planning the subproject
• Designing and defining KPIs
• Designing and developing models and visualizations of results using customer dashboards
• Developing and implementing data warehouse adaptations
• Deriving recommendations for action

Methods, technologies:

• Simulation
• Artificial intelligence
• Python
• R
• SQL
• Microsoft Power BI
• Amazon Web Services
• Elasticsearch
• PostgreSQL
• Databricks
• Multivariate statistics

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.

Project: Defect Generation on Test-Bench Images of Metal Surfaces Environment: Automated Visual Inspection (AVI), Metallurgy & Manufacturing

• Objective & Implementation: Designed, architected, and trained Generative Adversarial Networks (Pix2PixHD / SPADE) for image-to-image transformation. Targeted generation of synthetic material defects (e.g., cracks, inclusions, scale) on rough metal surfaces under real test-bench lighting conditions for privacy-compliant and efficient dataset expansion (data augmentation).
• Technical Design: Implemented robust Generative AI and computer vision pipelines in Python and PyTorch. Used semantic segmentation approaches for mask-controlled defect synthesis and subsequent evaluation with EfficientDet object detection models.
• Business Impact: Massive dataset upscaling (10x) without time-consuming and costly physical test-bench runs, while significantly improving the detection performance of automated inspection systems.

Technologies & Skills Used: Python | PyTorch | SPADE | Pix2PixHD | EfficientDet | Machine Learning | Semantic Segmentation | Computer Vision

• Supporting the International Web Presence of the BA (IntWeb) project in the area of quality management, with the aim of taking responsibility for the quality of processes and project results while considering BA standards. The main objectives of the project are to give professionals abroad a quick overview of their opportunities for moving to Germany and to enable them to take the necessary steps consistently and with digital support by providing access to services.

• Defining the general guidelines in the QA handbook

• Summarising test results in QA reports for PLA

• Analysing project results for improvement opportunities

• Quality management of requirements analysis (particularly processes, methods, and tools)

• Ensuring compliance with SERA requirements

• Creating a cross-project test concept

• Agreeing on sprint completion reports

• Formal review of work results in accordance with requirements and/or the project plan

• Contact person for internal audit, external audits by auditors, or BRH (Federal Court of Audit)

• Technologies: JIRA, Confluence, MS Office, GitLab, Kubernetes

The program supports the comprehensive realignment of the German Consumer Panel Services business. It combines a significant panel boost with the reprocessing of historical data and the integration of new receipt data. By significantly expanding and stabilizing the panel with the involvement of external partners, the aim is to improve the validity of the data base and create a reliable foundation for methodology, weighting and customer reporting. At the same time, historically grown processes for data delivery, OCR, matching, item QC, methodology and reporting are being harmonized, further developed technologically and reorganized. The goal is a scalable end-to-end landscape with higher data quality, clear responsibilities, reliable governance and sustainably manageable operational processes.

• Overall management of the restatement program, including the integrated roadmap as well as milestones, dependencies, risks and management decisions.
• Coordination of the panel boost and alignment of the required data deliveries, quality requirements and prerequisites for methodology, weighting and reporting.
• Alignment of business, product, data science, technology, operations and external partners around a shared target picture, aligned priorities and an integrated approach.
• Design of the organizational change triggered by the fundamental realignment of the data base, methodology and management logic, which has a lasting impact on established decision-making and collaboration patterns.
• Establishment and further development of governance, reporting and escalation structures as well as program-wide monitoring and operational processes for reliable management and sustainable handover.
• Management of critical data, technology and provider dependencies, including reprocessing, OCR transition and the timely synchronization of delivery, testing, methodology and reporting.
• Orchestration of international collaboration with teams and stakeholders in Germany, the United Kingdom, Portugal and Romania, as well as with external suppliers in Germany and Austria.

Impact Areas and Expertise: Program & Delivery Leadership, Business & Technology Alignment, Organization & Transformation, Governance & Sustainable Operations, Strategy & Target, Methodic Leadership, Transformation & Change Leadership, Executive Advisory

• Marketing Strategy: Lead the end-to-end analysis and evaluation of cross-channel marketing campaigns across the entire Customer Journey. My focus is identifying optimization potential and deriving clear, actionable recommendations that drive measurable business impact.
• Data Science & AI: Advanced predictive modeling (Churn, LTV), market basket analysis, clustering, and real-time AI-powered audience discovery utilizing RAG/LLMs.
• Marketing Analytics & Measurement: End-to-end attribution analysis, Marketing Mix Modeling (MMM), audience segmentation, conversion path analysis, and A/B testing across all major platforms.
• Data Engineering & Reporting: Designing and managing robust, multi-platform data pipelines (BigQuery, GCP) for data consolidation, automated dashboard generation, and critical API integrations.

GTM Services

As a coach, mentor, salesperson, networker and project manager, I support individuals and organizations in achieving their goals.

Multi-Agent Document-Generation Platform

Problem:

Turn a single prompt into a well-researched, structured and cited document, while keeping the user in control: every stage can be reviewed, corrected or revisited before the system moves on.

Architecture:

A multi-agent system orchestrated by a central controller. More than 20 specialised pydantic-ai subagents (understanding, structuring, planning, research, writing, assembly, cross-reference check, glossary, citation, reference table and more) pass results forward through a shared plan persisted in Postgres (asyncpg); a runner layer dispatches each task by name to its agent, and mechanical steps such as formatting, table of contents and list of figures are deterministic code instead of LLM calls. Provider (Anthropic or OpenAI) is a configuration setting, and responses stream over Server-Sent Events.

Hosting & Infrastructure:

Stateless container run as a Scaleway Serverless Container on a private network with managed PostgreSQL, object storage for finished documents and assets, and centralized log shipping (Loki / Scaleway Cockpit), provisioned with OpenTofu modules and deployed through GitLab CI; usage is metered per API key.

My Contribution & Key Decisions:

• Central decision controller: a satisfaction classifier turns the user's free-text feedback into a verdict (keep working, advance, cancel or revise an earlier task), and a middleware applies it to the plan. Plan progression supports jumping back to earlier tasks and re-running the stages after them.
• Research and writing fan-out: planning produces a plan from which a research-design agent generates individual research tasks and a writing-design agent generates individual writing tasks, each linked to the research it needs. Every task runs in its own dedicated agent with its own conversation history.
• Self-review and human-in-the-loop: after each step a critical-thinking agent reviews the output; the user can accept, refine, or ask questions about a critique before the plan advances.
• MCP integrations: two remote MCP servers, web search and internal document search, connected through pydantic-ai with retries and long-running tool-call timeouts. Classifier agents decide per task whether web search is needed, and a small model condenses raw search results into structured findings before they reach the writing agents.

Usage Metering:

Clients authenticate with an API key validated against a key-management service; consumption is charged in credits calculated from token usage per model plus a markup, and exhausted quota is answered with HTTP 429.

• Development of an AI-powered project organization tool for a civil engineering company that intelligently links project, task, tender, schedule, and document data through a knowledge graph.
• Implementation of AI features for document analysis, information extraction, context-based assistance, and voice-based data capture based on Microsoft Azure AI, reducing administrative effort, making information available faster, and supporting project teams in decision-making.
• Tech stack: Python, React, TypeScript, FastAPI, Claude Code, Codex, Graphify, PostgreSQL, Microsoft Azure AI Foundry, Azure OpenAI, Azure AI Speech, Azure AI Document Intelligence, Microsoft Graph, Microsoft Entra ID, Docker, Git, CI/CD.

• This project involved extraction of intelligence data to support report writing for a company that provides geopolitical, global, commercial intelligence. The data have been gathered from a number of resources (interview transcripts, online data, internal documents), and then a knowledge base has been build from it. This was the basis of a complex RAG system, that was evaluated against a golden dataset. Agents have been used to find out the contradicting intelligence, the statements supporting each other, and to store back the generated knowledge.

Used: Python, RAG, LangGraph, LangChain, deepeval, MCP

Prioritisation, Sequencing and Operating Model

a-connect client, Fortune 500 life sciences and agriculture group

• Consolidated competing business needs across five businesses into one prioritised agenda: assessed 1,000+ services against value, readiness and feasibility, weighed options, trade-offs and dependencies, and recommended the sequence of work, including what had to be redesigned or stopped before anything moved. Published case study.
• Aligned business, technology and data stakeholders on priorities and decisions across five businesses with separate leadership, P&Ls and competing agendas, onto one roadmap and six shared decision principles, without formal authority over any of them.
• Translated business intent into delivery-ready requirements and readiness standards that engineering, data and architecture teams could act on, with gates that stopped anything reaching production before the process, data and accountability behind it were fit.
• Established the sustainable prioritisation and progress-tracking approach the organisation still runs: service ownership, decision rights, escalation routes, governance forums and measurement, converted into a repeatable method that later teams operate without the author in the room.

• Task Engineering: Evaluating Coding Agents.
• Asset Creation: Building realistic task environments using datasets and files in German. Crucially, these assets must remain in the target language to genuinely measure multilingual handling.
• Prompting & Translation: finding failure points where AI does not work, in German.
• Implementation & Verification: Supporting the development of robust solutions (reference implementations) and write highly reliable, deterministic verifier scripts (using rubric-based judging only when strictly necessary).
• Calibration & Execution: Analyze execution logs and calibrate task difficulty (Easy to Very Hard) using standard Terminal-Bench run configurations against various model tiers (Haiku, Opus).
• Quality Assurance: Participation in a rigorous, 4-layer human quality control process (creation, human review, calibration review, and audit) alongside automated LLM-based checks to ensure fairness, grammatical accuracy, and benchmark integrity.
• Linguistic Review: Reviewing AI benchmark tasks across Hindi, Arabic, Japanese, Chinese, Czech and Turkish.