23.07.2025 aktualisiert


verifiziert
Premiumkunde
100 % verfügbarData Science and AI Engineer specializing in LLMs and advanced data pipelines
Chemnitz, Deutschland
Weltweit
MSc Chemistry (2012) with a focus on Theoretical and Physical Chemistry, ThePower MBA (2022-23)Skills
Künstliche IntelligenzAutomatisierungBig DataContinuous DeliveryContinuous IntegrationData MiningDevopsForecastingMachine LearningMarktwertOperational ExcellencePredictive ModellingProduktdesignReproduzierbarkeitAnforderungsanalyseSemantikZeitreihenanalyseDatenverarbeitungChatbotsData ScienceLarge Language ModelsAnmerkungenSuchmaschinenDaten-PipelineWeb Api
Large Language Model Development
Development and fine-tuning of custom language models and semantic search engines with integration of LLMs into data pipelines for various applications including ticket classification and compliance assistance.
Data Pipeline Engineering
Creation of robust data processing pipelines handling large datasets with focus on reproducibility and automation, including OCR systems and annotation pipelines that significantly reduce manual processing time.
AI Product Development
End-to-end development of AI products from conception to deployment, including generative AI chatbots, semantic search systems, and automated data extraction tools with business value integration.
DevOps and CI/CD
Implementation of continuous integration and continuous deployment practices ensuring reliable software delivery and operational excellence.
Time Series Analysis
Application of forecasting techniques and time series analysis for predictive modeling and trend identification.
Web API Development
Design and implementation of web APIs for data products enabling seamless integration with other systems and services.
Machine Learning Model Training
Training and deployment of various machine learning models with optimization for specific business use cases.
Development and fine-tuning of custom language models and semantic search engines with integration of LLMs into data pipelines for various applications including ticket classification and compliance assistance.
Data Pipeline Engineering
Creation of robust data processing pipelines handling large datasets with focus on reproducibility and automation, including OCR systems and annotation pipelines that significantly reduce manual processing time.
AI Product Development
End-to-end development of AI products from conception to deployment, including generative AI chatbots, semantic search systems, and automated data extraction tools with business value integration.
DevOps and CI/CD
Implementation of continuous integration and continuous deployment practices ensuring reliable software delivery and operational excellence.
Time Series Analysis
Application of forecasting techniques and time series analysis for predictive modeling and trend identification.
Web API Development
Design and implementation of web APIs for data products enabling seamless integration with other systems and services.
Machine Learning Model Training
Training and deployment of various machine learning models with optimization for specific business use cases.
Sprachen
DeutschMutterspracheEnglischMuttersprache
Projekthistorie
Support ticket classification using small local LLMs and rule-based filtering. Prototyped Compliance assistant using Data Bricks. Evaluated Google Cloud's Agentspace for internal knowledge management.
Development of a B2B procurement assistant chatbot as MS-Teams app. Implemented semantic search in a 100 million product database.
Developed patent explorer tool parsing patents and technical documents with automatic report generation on freedom to operate and strategic goals.