LLM agent systems for analytics and forecasting.
AI Engineer and Data Scientist specialising in LLM agent systems for analytics workflows. At InnoGames, I develop an agentic time-series forecasting solution that combines foundation models such as TabPFN with an LLM agent to incorporate business planning information into forecasts. I also develop an agentic workflow that builds Power BI reports, implements report changes, and validates the results. I bring ten years of analytics experience across telecommunications, finance, insurance, and gaming.
Foundation models and agent-compiled text covariates for game revenue.
My M.Sc. thesis evaluates whether covariates extracted from studio planning documents by an LLM agent improve three-month net revenue forecasts compared with the calendar-based features currently used at InnoGames.
Work in progress; submission December 2026. Further details once the thesis is submitted.
LLM agent systems for analytics, complemented by time-series forecasting with foundation models.
One of my current projects is an agentic time-series forecasting solution that combines foundation models such as TabPFN with an LLM agent, which turns versioned planning documents into forecasting covariates. My M.Sc. thesis at Leuphana University examines whether those text-derived covariates improve net revenue forecasts at InnoGames.
A second project is LLM-based tooling for analytics tasks such as building Power BI reports and preparing forecasting inputs. The workflows include explicit approval, validation, and escalation steps so that changes remain controlled and reviewable.
I am completing an M.Sc. in Management & Data Science at Leuphana University as a Deutschlandstipendium scholar, alongside my analytics and agent development work at InnoGames. From April 2027 I am available for full-time AI Engineer and Data Scientist roles in Germany.
Selected projects: LLM agent systems, knowledge graphs, and Bayesian modelling
What I work on
My projects span LLM agent systems, time-series forecasting, Bayesian modelling, and knowledge-graph applications. They include a multi-agent toolkit used by an analytics team, a knowledge-graph question-answering system, a hierarchical Bayesian customer lifetime value model, and a multi-agent assistant for company founders.
Agentic toolkit for Power BI report changes
Multi-agent Claude Code toolkit used across the analytics team, planning, implementing, and verifying Power BI dashboard changes in PBIP/TMDL without step-by-step human input.
ChefTreff AI Hackathon: Founder Assistant
Multi-agent assistant that helps founders launch a company in Germany, covering business plan, marketing plan, and legal documentation.
Knowledge Graph Question Answering
SPARQL-based question answering over structured knowledge graphs, enabling natural language queries over RDF knowledge bases.
KVG ML Route Modelling
Applied ML to model and predict transportation routes for a regional transit partner, combining geospatial data with predictive modelling.
Neo4j Graph Analysis of Artist Influence Networks
Graph database solution using Neo4j and Cypher to analyse artists' influence and cluster musical lineages.
Hierarchical Bayesian Pareto/NBD: Replication of Abe (2009)
Implemented and validated the hierarchical Bayesian Pareto/NBD model from Abe (2009) on the canonical CDNOW dataset.
ChefTreff AI Hackathon: Product Detection
Built in 24 hours: a computer vision pipeline for identifying broken or damaged objects from product imagery.
Writing on LLM agent systems and applied machine learning
Available in Germany from April 2027, preferably Hamburg, Munich, or Düsseldorf.
I am interested in AI Engineer and Data Scientist positions involving LLM-based systems, forecasting automation, or analytics platforms. I combine hands-on AI development with ten years of experience translating business requirements into maintainable data and analytics solutions.
My work fits six kinds of teams well:
- Insurance and reinsurance analytics. Underwriting segmentation at Absolute Insurance and current Bayesian forecasting research, applicable to Munich's insurance cluster and beyond.
- Gaming and consumer products. Revenue forecasting prototypes and analytics infrastructure at InnoGames in Hamburg, including Microsoft Fabric migration and Power BI dashboards.
- AI-native startups and applied AI labs working on LLM systems, agent architectures, and retrieval. I developed and rolled out a multi-agent toolkit now used daily by an analytics team, and my thesis develops an agent that converts planning text into inputs for revenue forecasting.
- Telecommunications and network analytics. Eight years at MTS covering market analysis and M&A across the Indian, Serbian, Slovenian, and Moldovan markets, relevant to telecommunications operators and network businesses, including in Munich.
- Global technology firms and platform teams in Hamburg, Munich, and Düsseldorf, where forecasting, applied ML, and production analytics scale across products.
- Startups and scale-ups where production ML and agent systems form the core product rather than a pilot.
I work in English at C1 level (IELTS 8.0) and in German at B2-C1 level. My analytics experience spans international teams in finance, telecommunications, insurance, and gaming.