Michael Nelz

- Delivered MLOps infrastructure and automation solutions, including MLflow server deployment, experiment tracking, logging optimization, and scalable pipeline execution across multiple ML projects with Azure Synapse and Pyspark.

- Engineered a Cashflow Forecasting platform to support financial planning, enhance forecasting stability, and optimize loan allocation decisions.

- Developed an end-to-end Demand Forecasting system that improved material allocation accuracy and optimized storage organization for operational efficiency.

Optimization of Car Price Estimation and AI Implementations
Customer: Farie AG
Duration: 06/2024 – 09/2024
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 from Google).
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.
Techstack: Python, API, selenium, Git, Prediction, Scrum, Kanban, GCP
SQL, GCP IAM, GCP VertexAI, LLM, GPT-4o, Prompt-Engineering,
Langchain, Huggingface, DockerPrediction of order intake
Customer: IJUNO GmbH | Duration: 03/2024 – 06/2024
Implementation 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.
Techstack: Python, Git, Timeseries, AWS S3, AWS Cloudwatch, AWS IAM

Data-Science-Component-Lead for Predictive Maintenance
Customer: global refractory provider | Duration: 01/2023 – 12/2023
Management of a team of 5 data scientists for the agile development
of a product for predicting maintenance intervals for high heat
furnaces including code reviews and pair-programming.
Job Interview of candidates for the data-science-team.
Supporting the Backlog-Refinement as Data-Science-Expert.
Story Estimation within the Data-Science-team.
Hands-On Implementation of Machine Learning Features, a.o.:
MLOps workflow with Azure-ML, model registry, Azure ML pipelines
and CI-CD pipelines via Docker and Kubernetes.
Enable automatic retraining for the AI-product.
- Senior Data Scientist for Predictive Maintenance
Customer: global refractory provider
Language: English | Duration: 03/2021 – 12/2022
Implementation of Machine Learning Features, a.o.:
MLOps workflow with Azure-ML, model registry, Azure ML pipelines
and CI-CD pipelines via Docker and Kubernetes.
Enable automatic retraining for the AI-product.
Optimization of training concepts including data preparation and
feature engineering.
Computer-Vision to generate features for models.
Introduced unit + end2end tests to the DS codebase.