Retrieval-Augmented Generation Experts in Hamburg

Freelance work for a large German family office

Built and further developed a modular B2B SaaS platform for professional wealth management and family offices, alongside freelance delivery of production-ready AI, data management, and automation solutions for the wealth management sector.

• Developed an AI governance framework for regulated finance and asset management workflows, aligned with DORA, BaFin-related governance expectations, and data protection requirements, including role definitions, access levels, and decision rules.
• Designed an agentic system with a locally operated open-source language model, including Qwen2.5 via Ollama, for secure querying of an asset database through text-to-SQL-to-text workflows.
• Built AI-supported analysis and reporting capabilities that generate structured answers, tables, and charts from asset data, with domain validation through resolver logic and RAG elements.
• Developed production-grade data import workflows for financial service provider data from CSV, PDF, and API sources, including validation, plausibility checks, and reconciliation with existing asset data.
• Solved the asset matching problem without a cross-system primary key through multi-stage validation rules and human-in-the-loop approvals.

Results:

• Secured EUR 250,000 in SaaS revenue in 2024, exceeding the forecast by 20%.
• Acquired family office clients with EUR 1.6bn in assets under management.
• Reduced manual effort for the largest client by approx. 3 days per month through automated data import and reconciliation processes.
• Reduced operational error risk through structured data validation, multi-stage asset matching, and human-in-the-loop approvals.

• Owning RAG, LLM-System, ML-ops-Pipelines for various startups in Insurance, Banking, Energy (KRITIS)

• Performed security assessments and penetration testing on Microsoft AI models for text, image, and video generation.
• Conducted prompt injection attacks through diverse input vectors, including crafted text, steganographic images, and manipulated visual elements (e.g., varying opacity and embedded content).

• Hands-on product and portfolio analyses with actionable recommendations
• Skilled in consulting, concept development, and agile project management
• Technical leadership & team empowerment – for smooth agile delivery with foresight and guardrails

• Lead developer of Prof. Valmed, the first LLM-powered medical device (utilising RAG on a medical corpus of 2.5M+ documents) to receive a CE certification.
• Designed and implemented cloud-native MLOps infrastructure for ENBW’s energy trading analytics division, enabling scalable deployment and monitoring of predictive models.
• Architected end-to-end testing and validation frameworks for AI/ML systems, ensuring quality, compliance, and robustness in critical and regulated applications.
• Conducted professional training on AI testing, EU regulatory frameworks, and quality assurance for production AI systems.

• Prototyped LLM/RAG document assistant; trained transcriptomics and proteomic data; used Git/Docker for reproducibility.
• Strengthened ML fundamentals applicable to omics (feature engineering, validation, leakage control).

• Architected and deployed LLM based AI agents, RAG pipelines, and vector search solutions for decision support across retail banking department.
• Developed and shipped robust AI pipelines with guardrails, error handling, monitoring, and fallback logic ensuring high reliability outcomes and compliance with data privacy.
• Developed and deployed ML models to identify transactional anomalies, improving fraud detection and risk assessment in high-volume datasets for credit risk modelling.
• Built, evaluated and fine-tuned ML models to generate propensity scores for customers used to drive personalized targeting campaigns for credit cards and personal finance/loan products.
• Developed an NLP pipeline using BERT embeddings and spaCy NER for SMS/email analysis and customer query logs.
• Trained machine learning models using Isolation Forest to classify user behaviour and detect anomalies.
• Extracted, cleaned, enriched and feature engineered datasets from different sources to build feature stores that powered ML model training.
• Led development of dashboards using Power BI, Grafana, and Prometheus to monitor model performances, KPI trends, and marketing metrics.
• Built multi-touch attribution models using logistic regression and time-decay weights to evaluate lead quality.
• Developed scalable ETL pipelines from CRM, T24, SAP, and ERP, supporting millions of monthly transactions.
• Integrated testing and CI/CD workflows for robust data pipeline deployment.

• Responsible for the redevelopment of a billing and validation software for prescriptions to fully check and analyze e-prescriptions for correctness (content, billing)

• System consists of multiple contexts running as services (Docker containers):

• Checking and processing data deliveries via FTP and email

• Management of invoicing, clearings, deductions and offsets

• Management and execution of validation rules and test sets

• Analytics based on Metabase

• Developer Stack: Kotlin, Vue 3 / Vuetify 3, ANTLR, Spring Boot 3, REST API, Gradle, Docker, GitLab, PostgreSQL, Kafka, Keycloak, Scrum, Grafana, Loki, Testcontainers, Prometheus