Data Scientists in Germany

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects

• Architected and deployed end-to-end machine learning pipelines across classification and prediction datasets, ensuring robustness and reproducibility through MLOps best practices.
• Contributed directly to LLM model output accuracy improvement by designing and engineering specialised prompts grounded in end-to-end ML and SciML pipeline logic.
• Developed training data for large language models by formulating coding problems that models could not resolve and subsequently documenting the correct solutions.

• Created a multi-agentic system supported by a knowledge graph to automate drafting of research papers
• Used multiple experts (OpenAI models) collaborating during document drafting
• Extracted useful information from the knowledge graph
• Technologies: LangChain, LangGraph, Smolagents, LlamaIndex, dspy
• Infrastructure: Terraform and GitHub Actions (CI/CD) on AWS
• Deployed initial application as a Streamlit app

• Designed and deployed enterprise Retrieval-Augmented Generation (RAG) applications using LangChain, LangGraph, vector databases, embeddings, and open-source LLMs served through vLLM on GCP GPU infrastructure.
• Built agentic AI workflows using LangGraph with planning, reasoning, tool execution, persistent memory, session management, and Human-in-the-Loop approval mechanisms.
• Developed LLM-powered automation systems integrating BigQuery, SQL pipelines, and external advertising APIs including Meta, TikTok, Amazon, Snapchat, Google, and Pinterest, reducing manual operational workflows.
• Architected multi-agent AI systems for enterprise analytics and decision-support workflows, enabling autonomous task execution and intelligent data interactions.
• Implemented retrieval optimization strategies including multi-retriever architectures, semantic search, context optimization, and query improvement techniques, improving response relevance by approximately 40%.
• Engineered structured prompting strategies, function-calling schemas, and validation workflows to improve reliability of multi-step LLM applications.
• Designed scalable AI services using Python, FastAPI, Cloud Run, Pub/Sub, BigQuery, Docker, and cloud-native deployment architectures.

• Delivered AI and data science solutions, including LLM-based chatbots and data pipelines, improving operational efficiency.
• Collaborated on product features, achieving measurable impact and maintaining strong client relationships.

• Development of 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

Development of AI-based and classical models for analyzing medical and patient data, including medication analyses, diagnosis analyses, forecasts, procedure analyses, dosage analyses, comorbidity analyses, prescription analyses, patient potential analyses, and referral profile analyses. Analyses in the area of Real World Evidence.

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

Methods, technologies: Simulation, Artificial Intelligence, Python, R, SQL, Microsoft Power BI, Amazon Web Services, Elasticsearch, PostgreSQL, Databricks, Multivariate Statistics

End-to-end responsibility for all products - concept, architecture, development, and production operation as the sole developer; in addition, customer meetings, proposals, and marketing.

Underwriting Copilot - AI assistant for industrial insurance (in production at customer sites)

• Supports underwriters in analyzing industrial insurance submissions - in production use at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, mixed document sets.
• Two-stage evaluation and observability pipeline (code assertions + LLM-as-Judge) that makes answer quality, retrieval accuracy, and citation integrity measurable in a regression-safe way.

Kaiki Menu Analyzer - Data intelligence platform (in production at customer sites)

• Automatically captures and analyzes menu data from around 25,000 German restaurants.
• Scalable 7-container architecture (FastAPI, partitioned PostgreSQL, Redis/RQ) with LLM-supported extraction of structured data from PDF, HTML, and images.
• Full CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas - GEO platform (in production at customer sites)

• Measures brand visibility across five AI engines (ChatGPT, Gemini, Perplexity, Grok, Claude), each augmented with web search, orchestrated as a DAG workflow pipeline (Dispatcher → Sub-workflows → Scoring → Report) with fail isolation.
• 6-container deployment (FastAPI, Celery, Redis, PostgreSQL); LLM cost estimation, PDF audit report, rule-based cross-signal insights (no extra LLM cost).

Data Pipeline & Analytics Platform - competitive analysis in the automotive aftermarket

• Automated data pipeline with gap analysis algorithms and role-based access control; 230+ tests.
• Backend with FastAPI, PostgreSQL, SQLAlchemy.

Product development (actively in progress)

BankingGPT - AI assistant for complaint management in cooperative banking

• Security architecture at the core: no AI draft reaches the customer without human approval - the approval decision is in auditable code, not in the language model (monotonic: the model may escalate, never downgrade).
• Real agentic building blocks, each with its own boundary: the model chooses tools itself through an MCP server (read-only, allowlist, capped, fail-safe); sensitive cases are handed off via an open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented by me) to a separate specialist agent (securities/law), which never lowers the review requirement (pinned by test).
• Evaluation-driven over ten analysis rounds; uncovered a security flaw through independent review and blind tests that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered in the conversation, sensitive ones escalate before generation; response latency < 7 s measured (local GPU STT/TTS).

Stack & production readiness: Python, pydantic-ai, FastAPI/Celery, PostgreSQL/pgvector, FastMCP, fasta2a, Docker; multi-tenant capable (physical vector isolation per tenant), PII encrypted, OWASP-LLM reviewed, 275 tests, CI/CD; vendor-portable (Ollama / EU Cloud Vertex).

After-Sales Assistant - agentic RAG/GraphRAG assistant on public OEM manuals (automotive after-sales)

• Genuinely agentic on LangGraph: ReAct agent with four tools and conversation memory - the model decides on its own whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher - decodes warning lights), or a workshop/booking service.
• Human-in-the-Loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and gets the driver's explicit confirmation - the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as CI gate: a three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first when there is a critical warning?) blocks the pipeline; provider-agnostic (OpenAI/Azure/Anthropic), FastAPI with token streaming.

Stack: Python, LangChain/LangGraph, Chroma, Neo4j, RAGAS/DeepEval, FastAPI, Docker.

• Developed a deep learning system with multi-view Basler cameras for markerless 3D pose estimation

• Enhanced the AI model monitoring solution to allow comparative analysis of model versions and full tracking of input variables with relative drift metrics for complete monitoring.
• Developed a custom LLM solution to automate the certificate of incoming goods of supply and support downstream analysis.
• Enhanced Digital Twin AI models to support model validation.

Skills: Python, Statistical Computation, Large Language Models (LLM), Machine Learning Engineering, Natural Language Processing (NLP), Data Wrangling, Data Visualization, Statistical Evaluation.

Tools: Python programming, Snowflake, Databricks, Microsoft Powerapps, Powerautomate, PowerBI, Scipy, Seaborn, Scikit-Learn.

Python, SQL, PySpark, Databricks, Databricks SQL, Delta Lake, dbt, Azure Data Lake Storage, Azure Machine Learning, Azure DevOps, Power BI, Git, MLflow

• Developed, validated, and optimized predictive analytics and classification models using Python (pandas), SQL, and modern ML frameworks.
• Performed data analysis, feature engineering, model validation, cross-validation, and stability analysis to ensure robust model quality and performance.
• Communicated model assumptions, results, uncertainties, and limitations to business units, management, and technical stakeholders.
• Built scalable data and machine learning workflows in cloud-based analytics environments using Databricks and Microsoft Azure.

• 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

• Technical and professional management of software and ML development; largely independent implementation of programming and guidance of the team and external project partners
• Design, creation, and preparation of training and test data sets from experimental image data and simulations
• Selection, implementation, training, validation, and testing of neural networks for image-based reconstruction and transformation
• Systematic evaluation, comparison, and optimization of various model architectures (convolutional neural networks, generative adversarial networks, autoencoders, transformers)
• Design and implementation of explainable AI analyses for model interpretability and robustness assessment (analysis of feature maps, augmentation studies, guided backpropagation)
• Presentation of the developed methods and results in project meetings and at international conferences

• Technical coaching for migration of activities from SAS to the Palantir Foundry platform
• Provided technical consulting and guidance during onboarding, delivered end-to-end knowledge in Palantir Foundry including pipeline usage
• Developed AI-driven tools for analysis of external parameters using machine learning techniques with TensorFlow and PyTorch
• Built an ETL pipeline in Python deployed on AWS and administered a SQL database
• Optimized business processes through process mining with Celonis by building frontend and backend dashboards, delivering data via SAS and SQL, setting up delta loads, and conducting enablement workshops
• Collaborated with sales and recruiting teams to identify new opportunities and assess applicants
• Organized internal and external events to promote teamwork and strengthen company presence
• Deepened technical skills in AI/ML, cloud-based solutions, and data engineering within the finance and reinsurance industry