Fine-Tuning Experts in Munich

Co-founded an AI-native language learning startup, defining the product vision, AI architecture and technical roadmap. Designed and built the AI and backend stack, including LLM fine-tuning pipelines, custom agentic workflows, and scalable inference infrastructure. First product currently in private beta.

• Research and develop models for chatbots, NLP and LLMs (e.g. Llama, Qwen, OpenAI)
• Enhance chatbots with RAG, in-context learning
• Supervised fine-tuning (PEFT, LoRA), Huggingface or Unsloth
• Advanced training methods: Test-time training, (transductive) active learning, reinforcement learning
• High-throughput serving with vLLM
• Apply embedding models (e.g. SentenceTransformers), similarity/vector search or vector DB or ranking (e.g. LlamaIndex, Faiss, LangChain)
• Generate and filter synthetic data, clustering
• Detect hallucinations
• Evaluate chatbot models (Rouge, BLEU, F1-Score, Recall, Precision)
• Visualization of experiments (matplotlib)

AI-driven automation of purchasing on a printing company's website, including selecting delivery times, order options, ordering, payment, and uploading print data from the Lumiz Cloud.

• Clarification of project goals, scope, and functional target vision for building the AI-based knowledge base.
• Deriving the initial architecture and implementation strategy for the Zasterbot chatbot, including defining the MVP and expansion phases.
• Developing a functional target vision for building a structured knowledge base and integrating a future chatbot.
• Deriving and prioritizing use cases for information retrieval and provision by the chatbot.
• Modeling data structures and flows for effectively organizing the knowledge base on the Base44 platform.
• Designing and implementing data models for storing and linking relevant information.
• Developing processes for extracting, analyzing, and preparing raw data for the knowledge base.
• Ensuring data consistency and quality as the foundation for the future chatbot.
• Planning the integration of large language models (LLMs) and retrieval-augmented generation (RAG) for precise and context-aware responses.
• Implementing features for analyzing and visualizing data from the knowledge base.
• Using the Base44 platform with JSON-schema-based entities and a flexible permission model.
• Implementing Deno functions for backend logic, event processing, and external API integration.
• Integrating OpenAI services for initial data analysis.

• Designed and implemented a full machine learning pipeline for churn prediction using the Telco dataset.
• Applied preprocessing techniques including missing value handling, categorical encoding, feature scaling, and PCA.
• Built and compared over 15 models (logistic regression, random forest, XGBoost, etc.) and evaluated them using accuracy, precision, recall, F1 score, ROC AUC, and PR AUC.
• Tuned hyperparameters with GridSearchCV, achieving 80.6% accuracy with random forest and XGBoost.
• Created visual reports (bar plots, heatmaps, radar charts) to interpret model performance and churn drivers.
• Exported reusable pipelines and trained models with joblib for deployment.

• Co-founded an AI venture focused on building production-grade LLM applications and agentic systems
• Designed and implemented multi-agent AI workflows for financial and trading applications
• Developed LLM-powered copilot architectures for portfolio analysis, trade management, and personalized user coaching
• Built on-device and edge-deployed inference applications, optimizing models for low latency, privacy, and resource-constrained environments
• Led system architecture decisions across model selection, orchestration, state management, and deployment

• Designed and evaluated high-quality prompts and completions for Large Language Models (LLMs), focusing on improving response accuracy, instruction-following behavior, and factual consistency.
• Annotated and rated LLM-generated outputs for grammar, coherence, relevance, and truthfulness.
• Developed RLHF-style preference data by ranking model completions to inform reinforcement learning fine-tuning cycles.
• Participated in prompt engineering experiments to assess the effect of instruction format, verbosity, and phrasing on model behavior.
• Conducted error analysis and quality assurance on large-scale NLP datasets, identifying edge cases and linguistic ambiguity affecting LLM performance.

• Created and refined technical and compliance-oriented datasets for AI, ensuring high-quality structured documentation.
• Conducted supervised fine-tuning (SFT) and RLHF tasks, maintaining strict alignment with industry and security guidelines.
• Produced detailed technical reports and feedback for audits and QA teams.
• Collaborated with cross-functional teams on documentation strategies for large-scale AI deployments.

• 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.

• Lecturer for the AI Manager in Insurance certification course

• Architected and implemented an enterprise-grade AI Agent Platform leveraging Retrieval Augmented Generation (RAG) architecture to enhance clinical data insights.
• Established robust CI/CD pipelines for LLM applications using CDK and Jenkins, significantly reducing deployment times.
• Implemented comprehensive observability solutions that increased agent reliability across pharmaceutical environments.
• Designed scalable AI workflows with advanced orchestration that optimized context handling for enterprise data sources.
• Technologies: AI Agents (LangChain, LangGraph, Bedrock, Smolagents, Streamlit); LLM Operations (Tracing, Testing, Evaluation, LangSmith, LangFuse); Infrastructure-As-Code (AWS CDK, Terraform, Typescript, Jenkins); Vectors, Embeddings, RAG (OpenSearch, pgvector, PDF Extraction)

• Agile setup of a multimodal analysis platform for training materials (video, audio, documents) using Scrum
• Extraction of context-relevant content based on user profiles & competency dimensions
• Personalized delivery of learning content to boost sales performance
• Close coordination with sales teams & stakeholders to validate features
• Use of Gemini, Whisper, Python & JavaScript, deployment on AWS, Perl for scripting data imports
• Integration into existing tools & CRM systems for smooth adoption
• Technologies used: Python, OpenAI, DB tech like PostgreSQL, CI/CD for Airflow DAGs, FastAPI

• Software development of a B2B SaaS for AI-based search in internal candidate pools of recruitment agencies
• Design of a multi-tenant, hybrid architecture with dedicated GPU servers and secure cloud integration
• AI-Engineering
• LLMOps
• Python
• FastAPI