Data Science Professional | Machine Learning Engineer | GenAI Engineer | Python Developer | Team-Lead
- Verfügbarkeit einsehen
- 1 Referenz
- 98€/Stunde
- 82223 Eichenau bei München
- DACH-Region
- de | en
- 06.02.2026
- Contract ready
Kurzvorstellung
Auszug Referenzen (1)
"Michael unterstützte uns bei einem ML-Projekt zum Demand-Forecast. Sehr kompetent, strukturiert, schnell und praxisnah – jederzeit wieder."
9/2024 – 6/2025
Tätigkeitsbeschreibung
This initiative represents a cutting-edge data science project aimed at crafting a scalable, robust, and highly accurate demand estimation model for better resource and delivery planning. Harnessing the full potential of Azure Cloud's advanced capabilities, the project employs state-of-the-art machine learning algorithms, Sentiment Analysis via LLMs, Model-Explanations via Dash and GenAI-Agents, large-scale data processing pipelines and cloud-based infrastructure to forecast demand across all business units. By optimizing production and logistics, this model drives efficiency and elevate decision-making.
- Creation of an end-to-end workflow tailored to accurately predict demand patterns and behaviors for all business units
- Two-Pronged Approach for Intermittent Demand Forecasting
▪ Binary Prediction: Identifying the occurrence of the next demand instance.
▪ Regression: Estimating the magnitude of the demand.
- Top-Down Forecast pronged together with Bottom-Up-Forecast to increase performance
- Implementation ensemble techniques to bolster prediction precision.
- Use of Azure Synapse for streamlined scalability and accessibility.
- Leveraging Large Language Models (LLMs) and Azure OpenAI to implement sentiment analysis for customer reports, enhancing qualitative insights.
- Implementation of a GenAI-Agent-System to use data and model logs to explain model outcome to model-users
- Deployment of the GenAI-Agent-System as plotly-Dash-App via Docker and Kubernetes
- Deployment of MLFlow-Tracking-Server via Docker and Kubernetes
Azure Synapse Analytics, Generative KI, Large Language Models, Machine Learning, Microsoft Azure, Predictive Analytics, Python
Geschäftsdaten
Qualifikationen
Projekt‐ & Berufserfahrung
1/2026 – 3/2026
TätigkeitsbeschreibungImprovements of the Demand and Cashflow Models and MLOps Tasks like Monitoring, Drift Detection and Performance Improvements
Eingesetzte QualifikationenPython
6/2025 – 1/2026
Tätigkeitsbeschreibung
This project develops a scalable, probabilistic, and highly reliable cashflow forecasting system to support strategic financial planning. By leveraging Bayesian modeling with Pyro, automated MLOps processes, and model explanations powered by GenAI, it generates precise, transparent, and uncertainty-aware forecasts. The solution strengthens decision-making, risk assessment, and financial resilience across the entire organization.
Techstack: Python, Pyro, Prognose, Scrum, Azure Synapse, Azure Open-AI, LLM, Prompt-Engineering, Langchain, Agentic AI, Plotly-Dash, Docker, FastAPI, Git
Apache Spark, API-Entwickler, Azure Synapse Analytics, Langchain, Large Language Models, Prompt Engineering
9/2024 – 6/2025
Tätigkeitsbeschreibung
This initiative represents a cutting-edge data science project aimed at crafting a scalable, robust, and highly accurate demand estimation model for better resource and delivery planning. Harnessing the full potential of Azure Cloud's advanced capabilities, the project employs state-of-the-art machine learning algorithms, Sentiment Analysis via LLMs, Model-Explanations via Dash and GenAI-Agents, large-scale data processing pipelines and cloud-based infrastructure to forecast demand across all business units. By optimizing production and logistics, this model drives efficiency and elevate decision-making.
- Creation of an end-to-end workflow tailored to accurately predict demand patterns and behaviors for all business units
- Two-Pronged Approach for Intermittent Demand Forecasting
▪ Binary Prediction: Identifying the occurrence of the next demand instance.
▪ Regression: Estimating the magnitude of the demand.
- Top-Down Forecast pronged together with Bottom-Up-Forecast to increase performance
- Implementation ensemble techniques to bolster prediction precision.
- Use of Azure Synapse for streamlined scalability and accessibility.
- Leveraging Large Language Models (LLMs) and Azure OpenAI to implement sentiment analysis for customer reports, enhancing qualitative insights.
- Implementation of a GenAI-Agent-System to use data and model logs to explain model outcome to model-users
- Deployment of the GenAI-Agent-System as plotly-Dash-App via Docker and Kubernetes
- Deployment of MLFlow-Tracking-Server via Docker and Kubernetes
Azure Synapse Analytics, Generative KI, Large Language Models, Machine Learning, Microsoft Azure, Predictive Analytics, Python
6/2024 – 9/2024
Tätigkeitsbeschreibung
Development of a robust, scalable, and highly accurate car price estimation model using advanced data science techniques by leveraging the advanced capabilities of Google Cloud Platform (GCP) and VertexAI. Automization of time-consuming national-vehicle-code matching via fuzzy matching supported by LLMs (GPT-4o and Gemma via Huggingface).
Proof of Concept for car-equipment-matching via LLMs to standardize the equipment overview on the website.
Proof of Concept for a car-suggestion Chat-Bot to help customers inform themselves about cars that fit their needs and suggest them fitting cars.
Docker, Git, Google Cloud, Langchain, Large Language Models, Prompt Engineering, Python, Scikit-learn
4/2024 – 6/2024
TätigkeitsbeschreibungImplementation of a monthly Sales-forecast based on economic factors. The results reach the accuracy of the manual forecast are used for decision making to saving time. Knowledge sharing regarding deployment on Azure-ML or AWS Sagemaker.
Eingesetzte QualifikationenAmazon Web Services (AWS), Data Science, Git, Microsoft Azure, Python
1/2023 – 12/2023
Tätigkeitsbeschreibung
Data Science Component Lead
Managing a team of 5 Data-Scientists for the Data-Science-part of a web-based product that provides predictions and suggestions to optimize the workflow of the customers.
Data Science, Management-Informationssysteme, Microsoft Azure, Python, Strategische Unternehmensplanung
3/2022 – 12/2022
TätigkeitsbeschreibungBereitstellung eines MLOps-Workflows mit Azure-ML-Workspaces, Model-Registry, Azure-ML-Pipelines und CI-CD-Pipelines über Docker und Kubernetes
Eingesetzte QualifikationenDocker, Kubernetes, Maschinelles Lernen, Microsoft Azure, Python
3/2021 – 2/2022
Tätigkeitsbeschreibung
- Optimization of Training-Concepts including Data-Preparation and Feature-Engineering.
- Implementation of Unit- and End-To-End-Tests for the Data-Science-Codebase.
Continuous Delivery, Maschinelles Lernen, Microsoft Azure, Python, Testen
1/2021 – 8/2021
TätigkeitsbeschreibungGeneration of data-insights from a website to track customer-usage and improve customer-experience on the website and report insights
Eingesetzte QualifikationenC#, Google Cloud, Python
6/2020 – 12/2020
TätigkeitsbeschreibungRisk-Management: For an optimal planning of future purchasing and sales, a Prediction of Risk based on previous kpis, interest-rates simulations and the market situation was implemented.
Eingesetzte QualifikationenFinanzanalyse, Statistiken, Python, Simulation Geschäftsprozesse
1/2020 – 6/2020
Tätigkeitsbeschreibung
Prediction of Airpolution
To improve usability and performance of an old programm, a renewal and improvement of the prediction-service for predicting the airpolution was implemented.
Data Science, R (Programmiersprache)
8/2019 – 12/2019
Tätigkeitsbeschreibung
Prediction of payments
In order to improve planing of expenses, a prediction service was set up to predict the payments to the customers musicians.
Data Science, Python, Statistiken
6/2019 – 10/2019
Tätigkeitsbeschreibung
Measurement of discount-campaigns
To get more insights on marketing-campaigns and improve their impact, a new statistical measurement for campaign performance was built in order to predict and improve campaigns.
Data Science, Python
11/2018 – 5/2019
Tätigkeitsbeschreibung
Document Recognition
Implementation of a fully automated, deep-learning document recognition with Python and Tensorflow system for insurance applications to check whether all validity-measures, like identity-cards, are fulfilled.
Apache Hadoop, Apache Spark, Keras, Python, Tensorflow
8/2018 – 12/2018
Tätigkeitsbeschreibung
Best next offer for credit offers
The credit-institute needed a system where customers would get the best credit for their needs based on their information and history.
Finanzanalyse, R (Programmiersprache)
3/2018 – 10/2018
Tätigkeitsbeschreibung
Prediction of Prices
In order to provide a self-regulation app to the customers, a service for predicting Prices of insured loss was implemented.
Apache Hadoop, Apache Spark, Microsoft Azure, Python
1/2018 – 3/2018
Tätigkeitsbeschreibung
I developed a training where the participants and I go over the statistical basics (day 1), data-science vs data-mining (day 2) and data-science deep-dive (day 3).
It was initially thought for the Internal Knowledge sharing but was then also provided to customers outside the company.
R (Programmiersprache), Latex, Python
Ausbildung
LMU München
München
LMU München
München
Über mich
Continuous Improvement is key, as well in agile software-development when creating a software product and in Data-Science when staying up-to-date with the fastly evolving environment of AI.
Professional skills:
- Management of Data-Science-Teams (1 + years)
- Machine Learning, Deep Learning, Computer Vision with Python (scripting + oop) (10 + years including studies)
- GenAI, NLP with Python (2 + years)
- Agile software development (6 + years)
- ML-Ops on Azure (6 + years)
- ML-Ops on AWS (2 + years)
- Teaching Data-Science (Coding Workshops, Courses) (4 + years)
Supporting Skills:
- Software-Development with Java, C#, PHP, Bash-Scripting (10 + years)
- Unit- and E2E-testing (3 + years)
Weitere Kenntnisse
Cloud Services: Microsoft Azure, Amazon Web Services
Azure: Azure-ML, Databricks, Dev-Ops, Functions, Factory, App-Insights, Blob-Storage, Virtual-Machines, Azure-Cognitive Services
AWS: Amazon Sagemaker
Software Engineering: CI-CD-Pipelines, Kubernetes, Docker, Postman
Big Data: Cloudera, Hadoop, Hortonworks, Spark (pyspark)
Databases: Hbase, Hive, Microsoft SQL Server, MySQL
Software Development: Python, R, C#, SQL, HTML+CSS, Latex, Matlab
Data-Science-Tools: SKLearn, Tensorflow, Pytorch, Plotly, Pytest, PyQT, Dash, Flask, GGPlot, R-Shiny
Persönliche Daten
- Deutsch (Muttersprache)
- Englisch (Fließend)
- Europäische Union
Kontaktdaten
Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.
Jetzt Mitglied werden