Über mich
I empower European Technology Providers to build market-leading AI software & Industrial Asset Operators to maximize asset ROI. My unique journey from astrophysics to industrial AI delivers pragmatic, high-impact solutions that translate complex data into measurable business advantage.
🏆 My mission is to bridge the gap between cutting-edge AI methodologies & the practical realities of industrial applications, ensuring solutions are not just innovative, but also robust, scalable, & instrumental to your success.
How I Deliver Value for You:
✅ For Technology Providers: Elevating your software with market-leading AI features (e.g., advanced anomaly detection, predictive capabilities, GenAI integration) that accelerate time-to-market, enhance user experience, & create distinct competitive advantages.
✅ For Asset Operators: Formulating data-driven strategies & providing independent guidance to optimize asset performance, significantly reduce operational risks, implement effective Predictive Maintenance solutions, & enhance overall profitability.
Proven Impact Highlights:
⭐ Enabled 2 TWh in Annual Energy Savings by architecting the core AI diagnostic algorithms for a leading industrial SaaS platform.
⭐ Drove 90% Diagnostic Accuracy by pioneering hybrid Digital Twin models that blend advanced statistical and physics-based AI.
⭐ Powered Global AI Deployment to 75+ Assets by building the foundational data engineering and scalable ETL pipelines.
With over 8 years of dedicated experience transforming petabytes of complex data (from cosmic signals to industrial sensors) into actionable insights, I bring a blend of deep statistical rigor & pragmatic engineering.
👉 Ready to achieve optimal asset performance or AI product leadership?
Let's discuss your AI projects
Skills
Expert:in
Fortgeschritten
Grundkenntnisse
Projekte
Shaping AI Strategy for Enhanced Mobile User Interaction (NLP R&D)
LetsVibe App · Gesundheit und Soziales · bis zu 10 Mitarbeiter:innen
2025
For a mobile application provider (LetsVibe), I led an R&D initiative to explore AI-driven enhancements aimed at improving user interaction quality and engagement within their platform.
The Business Imperative: The client sought to innovate by integrating intelligent features to support users in crafting more effective communications, thereby aiming to increase user satisfaction, positive interactions, and overall app stickiness.
My Strategic Solution & Implementation: As an AI consultant, I spearheaded the initial research, feasibility assessment, and strategic planning for a novel in-app user support tool. My contributions included:
- Leading applied R&D into Natural Language Processing (NLP) and advanced sentiment analysis techniques, evaluating models to assess qualitative aspects of user-generated text.
- Conducting thorough analysis of existing (anonymized) user interaction data to identify patterns and inform AI model development strategies.
- Developing foundational data processing approaches and establishing initial machine learning baselines to benchmark the potential of more complex AI solutions.
- Delivering a comprehensive analysis of research findings, including the inherent challenges of evaluating model performance with organic interaction data, and authoring a strategic proposal for future AI feature development. This roadmap emphasized the critical need for high-quality, targeted evaluation data to ensure robust model training and validation, and also included considerations for potential GenAI applications.
Value Delivered & Capabilities Showcased:
- Provided the client with crucial insights and a strategic framework for their AI product development lifecycle, enabling informed decisions about future AI/NLP feature integration.
- Demonstrated expertise in rapid AI concept validation, NLP/sentiment analysis R&D, and data-informed strategic planning for technology providers looking to enhance software with intelligent capabilities.
- My work helped clarify the technical path and data requirements for developing a potentially high-impact user engagement feature.
Key Learnings for Technology Providers: This project underscored the importance of early-stage R&D and strategic data planning when exploring novel AI features. Addressing data quality and evaluation challenges upfront is critical for de-risking development and ensuring AI initiatives can deliver tangible product value.
Key Technologies & Methodologies: Python, Natural Language Processing (NLP), Sentiment Analysis, Machine Learning (Scikit-learn, Pandas), AI Product Strategy, Feasibility Studies, R&D, Data Analysis, Strategic AI Roadmapping.
Developing an AI-Powered Q&A Companion with Generative AI (RAG)
· Gesundheit und Soziales
2024
This personal project, “Nutrify Your Life,” involved developing an end-to-end Retrieval-Augmented Generation (RAG) system to transform an extensive, science-based blog library (1200+ posts) into an interactive, conversational knowledge source.
The Challenge & Learning Objective: To master the practicalities of building a sophisticated RAG system capable of making a large, unstructured, domain-specific knowledge base accessible via natural language, and to explore architectures directly applicable to industrial use cases.
Solution & Key Methodologies: I independently designed, developed, and deployed the “Nutrify Your Life” Q&A chatbot. This involved:
- Systematic web scraping, parsing, and chunking of blog content.
- Constructing a knowledge base using sentence embeddings and a LanceDB vector database.
- Implementing an advanced retrieval pipeline with hybrid search (vector + keyword FTS) and Cross-Encoder reranking, including sentence-window retrieval for richer context.
- Integrating with fast LLMs (via Groq API, e.g., Llama3) for accurate, context-aware answer synthesis with source citation, guided by careful prompt engineering.
- Developing a user-friendly Streamlit interface, MongoDB-backed monitoring dashboard, and containerizing the application with Docker for deployment on Streamlit Cloud.
- Rigorous offline evaluation of retrieval (Hit Rate, MRR) and RAG quality (cosine similarity).
Demonstrated Capabilities:
- Successfully built and deployed a fully functional AI application, demonstrating end-to-end expertise in GenAI application development, from data ingestion to LLM integration and UI creation.
- This project solidified my practical skills in the complete GenAI development lifecycle.
- Relevance for Asset Operators & Technology Providers: The RAG methodology & architecture demonstrated here offers transformative potential for industrial applications, delivering significant efficiency gains and democratizing knowledge access. It is directly applicable for:
- Technology Providers: Integrating intelligent AI assistants into software to provide instant, context-aware support, answer complex user queries based on product documentation, and reduce support overhead.
- Asset Operators: Creating powerful internal knowledge bases from technical manuals, maintenance logs, safety procedures, and compliance standards, enabling rapid troubleshooting, improved decision-making for field engineers, and streamlined onboarding for new personnel.
Key Technologies & Methodologies: Generative AI (RAG), Python, Streamlit, LLM APIs (Groq), Sentence Transformers, Vector Databases (LanceDB), Hybrid Search, Cross-Encoder Reranking, Prompt Engineering, Data Scraping/Processing, MongoDB, Docker, Evaluation Metrics (Hit Rate, MRR).
Enhancing a Core Diagnostic Engine with Advanced Anomaly Detection
· Industrie und Maschinenbau · 50–100 Mitarbeiter:innen
2022 — 2024
For a leading SaaS provider of industrial diagnostics, I helped enhance their core AI product by designing and deploying a next-generation anomaly detection and MLOps framework.
The Strategic Challenge: The company’s mission is to provide real-time, reliable diagnostics for complex industrial assets. To maintain market leadership and scale its impact, there was a critical need to enhance the core diagnostic engine with more advanced, scalable, and interpretable machine learning algorithms.
My Strategic Solution & Implementation: I spearheaded the algorithmic strategy and was a key driver in establishing a robust MLOps framework for the core product. My contributions included:
- Designing, benchmarking, and deploying a suite of advanced anomaly detection algorithms (causal and non-causal, e.g., Isolation Forest, PCA-clustering) tailored for complex industrial data.
- Developing a novel mock-fault injection framework for rigorous pre-deployment validation, ensuring the high reliability required for mission-critical systems.
- Establishing and benchmarking robust MLOps pipelines for efficient model training, scalable deployment, and continuous performance monitoring.
- Experimenting with different explainability frameworks to pinpoint anomaly drivers, a key feature for end-user adoption and trust.
- Improving CI/CD practices and transitioning the algorithmic codebase to a newer Python version.
Measurable Business Value Delivered:
- Contributed directly to the core technology that enables the company to identify 2 TWh of energy losses annually across its global fleet of 75+ industrial assets.
- Significantly improved anomaly detection accuracy and model interpretability, reinforcing the platform’s publicly stated 90% diagnostic accuracy and leading to more reliable, actionable fault warnings for end-users.
- The robust MLOps processes reduced model deployment times and enhanced platform reliability, enabling faster delivery of value to clients.
- Strengthened the company’s position as an innovator in the industrial AI space by integrating cutting-edge ML techniques into its core product.
Key Learnings for Asset Operators & Technology Providers: This project underscored the critical importance of robust MLOps, mock-fault validation, and model explainability for building trustworthy and scalable AI in mission-critical industrial systems.
Key Technologies & Methodologies: Python, Advanced Anomaly Detection Algorithms (AAKR, Isolation Forest, Clustering, Causal Methods), Strategic MLOps Design (Kubernetes, NATS, GitHub Actions, Seldon), Custom Mock-Fault Generation & Validation, Model Explainability (SHAP), Performance Benchmarking, CI/CD (GitHub Actions).
Berufserfahrungen
Data Scientist · Vollzeit
Metroscope (leading SaaS provider of industrial diagnostics) · Industrie und Maschinenbau · 50–100 Mitarbeiter:innen
Januar 2022 — Februar 2024
Led the development of AI-driven SaaS products for predictive maintenance (PdM) in the energy sector. My work contributed directly to doubling the company's product portfolio, increasing revenue by 60%, reducing digital twin calibration costs by 50%, cutting data ingestion times by 90%, and reducing operational costs while increasing client satisfaction.
- Launching a flagship Product: Led algorithm development for a new SaaS product for early anomaly detection. Designed & benchmarked a suite of models (e.g., anomaly detection) & developed a novel mock-fault validation framework to ensure reliability. Established robust MLOps pipelines for scalable training & deployment, directly contributing to doubling the product portfolio.
- Enhanced digital twin ROI: Enhanced digital twin accuracy by integrating advanced statistical models with existing physics-based systems. Developed a novel "best-performance" filtering technique using custom clustering to isolate optimal training data. This hybrid approach reduced model calibration times & customization costs by over 50% while improving diagnostic accuracy.
- Industrializing Data Ingestion: Architected & deployed a universal ETL pipeline to industrialize the ingestion of diverse client sensor data. The solution featured adaptive parsing, robust data validation, & automated error handling. It cut data processing times by over 90%, significantly accelerating client onboarding.
- Demand Forecast POC: Delivered a rapid Proof of Concept (POC) to evaluate ML models power plant output forecasting. Engineered impactful features, including lagged performance metrics, which improved accuracy baselines. It provided crucial de-risk R&D choices for a new forecasting product.
Research Lead (Astrophysics) · Vollzeit
CNRS & University of Paris-Saclay · Bildung und Wissenschaft
Januar 2018 — Dezember 2020
Led data-driven research within a 16-person team, architecting ETL pipelines & applying advanced modeling to extract insights from complex datasets, resulting in first-author publications & secured new research funding
- X-ray Data Analysis Project: Led the analysis of a unique cosmic structure using advanced techniques for background modeling & signal extraction. Designed a custom Python package for profile fitting (MLE, Bayesian inference) to robustly estimate physical parameters, leading to a first-author publication in a top-tier journal.
- Securing Research Funding: Authored & led a successful proposal to the European Space Agency(ESA) for observing time. Developed a sophisticated ETL pipeline (Python/SQL) to identify the target & created a data-driven justification with detailed signal predictions, securing resources against stiff international competition.
- Cosmic Web Detection Project: Contributed specialized scripts & expert guidance to a landmark study that achieved the first statistical detection of X-ray emission from cosmic web filaments. My contribution was instrumental in validating the analysis & ensuring the robustness of this major scientific discovery.
- Automating Analysis Workflows: Developed a reusable, automated pipeline for the team to standardize the processing of space telescope data, orchestrating complex software environments & significantly improving research efficiency & reproducibility
Research Lead (Astrophysics) · Vollzeit
KIAA (China) & MPA (Germany) · Bildung und Wissenschaft
April 2015 — September 2018
Pioneered a novel statistical method for analyzing faint signals in massive datasets, resulting in an award-winning, first-author publication & securing multiple competitive research grants.
- Advanced Signal Analysis: Engineered a new analysis method to isolate faint signals of large-scale structures from complex cosmic background data. Developed custom models to accurately subtract instrumental noise, revealing insights inaccessible via standard techniques.
- Diagnostic Tool Development: The resulting method served as a new diagnostic tool that statistically characterized previously unresolvable structures. Its significant potential was validated by outperforming conventional approaches, as detailed in my publications
