Vector Database Experts in Germany

• 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

Evidence-led health intelligence platform turning published research into personal health protocols. It scores 430 habits, foods, and supplements against the studies behind them, and moves the score when the evidence moves. Built solo.

• Built the daily ingestion pipeline across PubMed, bioRxiv, and medRxiv: 43,000+ papers from 3,400+ journals processed into 230,000+ typed evidence claims, each one traceable back to the study it came from.
• Designed the six-factor evidence scoring model and the public changelog behind it, so no recommendation ever appears without the papers underneath it. 23,000+ grade changes recorded and explained to date.
• Shipped an entity information model connecting every intervention to its mechanisms, biomarkers, and outcomes: 118 biomarkers with region-specific reference ranges, 77 mechanisms, 32 graded outcomes.
• Built the personalisation layer: blood panel ingestion that reads lab PDFs with a vision model and corrects results for draw time against the user's wake anchor, plus Oura, WHOOP, and Withings integration for daily readiness context.
• Operate eleven specialised review agents over the corpus and codebase, covering paper curation, retrieval quality, health-claim compliance across EU and US regimes, and security.
• Shipped the Evidence Assistant, a RAG assistant that answers from the claim database and cites the underlying papers, plus a B2B practitioner tier, an Expo React Native app, and localisation across 3 languages and 7 markets.

Stack: Next.js 16, TypeScript, Supabase, pgvector, Anthropic Claude, Vercel, DeepInfra.

AI-supported document processing and inventory management integration

Design and development of an AI-supported application for the automated processing of delivery and invoice documents, connected to SelectLine ERP. Documents are analyzed using AI, matched with orders and line items, and prepared for posting goods receipts.

IMPACT:

• Automated extraction of structured order, delivery and invoice data from PDF and image documents
• Automatic and manual mapping of documents to orders and order line items
• Integration with SelectLine ERP for order import, status synchronization and goods receipt postings
• Traceable processing through separate analysis, mapping and posting processes as well as technical logging
• Development of a containerized end-to-end architecture with AI analysis, workflow automation and relational data storage

KEYWORDS: AI, document analysis, OpenAI, n8n, SelectLine ERP, FastAPI, Python, JavaScript, MariaDB, Docker, REST API, PDF, OCR, mapping, inventory management, goods receipt, workflow automation

• Architected and deployed private cloud data platform on VMware vSphere, integrating Greenplum MPP, Apache Kafka, Kubernetes, and Apache Solr, and developed real-time ingestion pipelines with Kafka Connect and Schema Registry.
• Led Oracle Exadata to Greenplum migration, rearchitected data models, optimized storage, implemented RabbitMQ with Debezium for CDC, and deployed VectorDB for Generative AI.
• Designed and executed multi-cloud migration PoC across AWS, Azure, and GCP, defined KPIs for throughput, latency, and cost efficiency, executed bulk data transfers, validated analytics and streaming workloads, and delivered full-scale architecture recommendations.
• Assessed legacy on-premises infrastructure and designed modern cloud-native data platforms using Greenplum and containerized microservices, advising on scalability, disaster recovery, and high-availability.

• LLM-based features for automated CO₂e data extraction from unstructured documents (70% reduction)

• Agentic AI pipeline for automated Scope 3 emissions calculations with 150.000+ validated data records

• Intelligent API workflows for real-time carbon footprint calculations in ERP and ESG systems

• ML algorithms for predicting emissions hotspots and optimizing product design

• Automated data validation pipelines with NLP for quality assurance of CO₂e datasets

• Led a 15-person cross-functional team in developing 10+ AI features

• Strategic product planning and AI roadmap with 35% shorter time-to-market

• Stakeholder management with DAX companies (40% higher satisfaction, 95% retention)

• On-time project delivery with 95% budget adherence through data-driven backlog management

• Agile methods (Scrum, Kanban) with continuous AI/ML integration (25% increase in team velocity)

• Product-market fit for AI features through A/B testing and analytics (60% higher adoption rate)

• Fully on-premises LLM document-examination platform for a compliance-critical banking domain: agentic LangGraph pipeline with deterministic verification, every AI judgment structured and source-anchored; ~960 automated tests, zero data egress
• GPU throughput engineering (quantized serving, speculative decoding, prefix caching): 9.5x extraction speed-up, 500+ multi-document case files per day on a single A100
• AI-native EDI/EDIFACT integration platform (~116k LOC Java 25 / Spring Boot 4, 1,900+ tests): LLM-drafted partner mappings machine-verified before go-live (DFDL conformance, field-coverage checks, dry runs), ~99.5% byte match on real customer files — replacing weeks of manual mapping per partner

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.

• 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

• Delivered a new notifications platform implementation built from scratch to replace existing and upcoming services
• Collaborating with other teams to integrate more domains

Tech stack:

• Data: Scala 3, Apache Kafka, Python, Airflow, Astronomer
• BE-FE: TypeScript, NestJS, Java, Spring Boot, Vue
• Dev-ops: AWS, PostgreSQL, Docker, GitHub Actions, Kubernetes, Helm, ArgoCD

Embedded Analytics & AI-assisted BI

Design and development of an integrated analytics solution based on ASP.NET Core, Power BI Embedded, and LLM services to provide context-based business information.

Development of an AI agent with Function/Tool Calling for the secure orchestration of REST APIs, SQL data sources, and technical services within defined business processes.

Building automated BI workflows including workspace management, deployment processes, and scheduled refresh via the Power BI REST API.

Implementation of secure service-to-service communication with Microsoft Entra ID and Service Principal, and integration into existing enterprise system landscapes.

Technologies: ASP.NET Core, C#/.NET, Power BI Embedded, Power BI REST API, LLM API, AI Agents, Function/Tool Calling, Entra ID

Statistical Forecasting Algorithm

• Improvement of an statistical probabilistic forecasting algorithm for sales + evaluation
• Migration from R/On-premise to Python/Snowflake
• Productionalization on Snowflake in cooperation with data engineers & DevOps

Monitoring Dashboard

• Data engineering for preparation & provisioning of necessary data/resources on Snowflake
• Development & deployment of a Streamlit dashboard in Snowflake

ML-based Probabilistic Forecasting on Vertex AI

• Development of a ML-based probabilistic forecasting algorithm from scratch
• Implementation of MLOps pipeline in Kubeflow on Google Cloud Vertex AI

Tech Stack: Python, Snowflake/Snowpark, R, Streamlit, Gitlab/Gitlab CICD, Terraform, Google Cloud, Vertex AI (aiplatform SDK, gcloud CLI, feature store, model registry, etc), kubeflow

Scope: Embedded as FP&A Data & AI Architect within the Finance function of a major European refrigeration manufacturer, leading the transformation of manual, fragmented financial reporting into an automated, governance-driven intelligence platform. Driving the shift from Excel-based controlling to structured data architecture, Power BI analytics, and AI-assisted financial operations.

Financial Data Integrity & ERP Governance

• Initiated and led GL vs. subledger reconciliation investigations, identifying and resolving structural mismatches between General Ledger and subledger data that had gone undetected prior to engagement
• Conducted asset analysis to identify items missing from General Ledger postings, surfacing gaps in fixed asset tracking and period-end completeness
• Validated SAP reports, establishing baseline data quality standards for Finance team consumption
• Established systematic SAP data validation framework ensuring ongoing integrity between ERP postings and downstream reporting outputs

Finance Reporting Transformation

• Designed and implemented a structured Transformation Project approach for converting manual Finance reports into fully automated processes
• Created and owns the Data Reporting Audit Log; a centralized tracking system capturing report owners, stakeholders, data sources, manual effort estimates, and automation opportunity scores across the Finance function
• Mapped the full reporting landscape identifying quick-win automation targets and strategic Power BI migration candidates
• Actively reducing manual Excel and PowerPoint dependency across FP&A workflows; replacing point-in-time snapshots with live, governed data models

Power BI & Analytics Enablement

• Introduced and presented Power BI as the strategic reporting platform to Finance leadership, building internal buy-in for the BI transformation roadmap
• Designed initial Power BI architecture aligned with SAP, Salesforce and Oracle data structures and FP&A reporting requirements
• Established report ownership, governance documentation, and data lineage standards enabling sustainable self-service analytics across the Finance team

Transformation Infrastructure & Collaboration

• Configured and deployed Jira as the transformation project management hub, establishing structured sprint workflows, backlog management, and progress visibility for Finance IT initiatives
• Proposed and initiated a dedicated FP&A Communication & Transformation Hub, a structured cross-functional forum aligning Finance, IT, and business stakeholders around the reporting transformation roadmap
• Positioned the Finance function as an active driver of data governance and digital transformation within the broader organization

Outcomes

• GL/subledger reconciliation gaps identified and investigation framework established within first two weeks of engagement
• Data Reporting Audit Log deployed; first structured inventory of Finance reporting landscape in company history
• Power BI transformation roadmap presented and approved by Finance leadership
• Jira-based project governance live; Finance transformation now tracked with full sprint visibility

Technologies: SAP FI/CO · Power BI · DAX · SQL · Excel (advanced) · Power Query (M) · Power Automate · VBA · Jira · Microsoft 365 · SharePoint · Salesforce (Sales Data) · Oracle HCM · Python

• Root cause analysis of complex business, technical, and data-related errors in PowerCloud across process, booking, and system boundaries.
• Data-driven management of payments and receivables; contributed to reducing historical receivables from over 100 Mio. EUR to under 25 Mio. EUR.
• Identification of automation and straight-through processing potential at the interface between business departments, IT, and external service providers.