Polars Experts in Germany

Independently built a data platform with cross-system process monitoring.

• Designed the Bronze/Silver/Gold architecture and Python-based pipelines for diverse operational sources.
• Cleaned, harmonized, and validated data; processed and stored it in Parquet format.
• Tracked data history and built business-focused fact and dimension models for traceable reporting.
• Automated data delivery with Python and Power Automate (desktop and cloud); used SharePoint for archiving and data access.
• Developed the Power BI solution from data preparation through to visualizing process statuses, work progress, and deviations.

Technologies: Python, SQL, Parquet, Power BI, Power Query, Power Automate, SharePoint, Copilot

• Led end-to-end delivery of ML/AI applications for the QuantistryLab simulation platform, from requirements definition and solution design to development, testing, deployment, and production support, coordinating efforts across back-end, DevOps, and ML teams
• Designed and implemented a compound search system with an open-weights LLM, the Pydantic AI agent framework, and the Model Context Protocol (MCP), exposing it through FastAPI endpoints
• Deployed and configured vLLM-based LLM serving on Kubernetes
• Built CI/CD pipelines and Helm charts to automate deployments across staging and production environments
• Instrumented the search system with OpenTelemetry spans and traces, integrating with the Honeycomb observability platform to monitor component-level latency and functional errors
• Developed a custom evaluation dataset and implemented evaluations for retrieval relevance, answer correctness, tool-call accuracy, and end-to-end task success
• Reduced infrared spectrum prediction time by 83% (from 60 to 10 minutes) by replacing a quantum-mechanical model with a pretrained graph neural network; fine-tuned the model using PyTorch, built and containerized the inference pipeline with Docker, and integrated it into the platform
• Implemented an MLflow model registry with MinIO-backed artifact storage
• Advised sales and science teams on ML/AI applications for prospective client projects, providing technical expertise to shape proposed solutions and prototypes

Technologies: AWS, Hetzner, Kubernetes, Helm, Docker, vLLM, Pydantic AI, MCP, Qwen, Llama 3, MLflow, MinIO, GitHub Actions, Python, FastAPI, OpenTelemetry, Honeycomb, PyTorch, Polars, pytest

Creation of workflows for generating the data basis for the article import of a web shop: combining data from several sources, analyzing the requirements, designing the process with Jupyter Notebooks and Knime. Also creating code for automation in Python using Polars and Pandas.

Processing the source data, filtering and merging the source files and creating the needed intermediate products, creating the upload files, plausibility checks, quality checks.

Technologies used: PyCharm, Python, Jupyter Notebooks, SQL, Knime. Pandas, Polars

• Architecting and developing SaaS platform for graphical definition and execution of pandas data processing pipelines
• Developed POlyglott, an open-source Python CLI tool for translation workflow management featuring PO file parsing, quality linting with glossary enforcement, and DeepL API integration for machine translation
• Developed web application for material compliance management (EU REACH) using Django and modern web technologies
• Built automated infrastructure platform using Proxmox, Terraform, and Ansible — VM provisioning, configuration management, internal DNS, and fleet-wide security hardening across multiple subnets

• Designed and implemented a robust Python-based data processing framework that supported the transition from R to Python and significantly improved data science productivity by providing maintainable, standardized modules for frequently used workflows, following coding best practices and DevOps principles
• Evaluated, trained, and deployed machine learning models on cloud platforms and edge devices, enabling fully automated mid-infrared (MIR) data evaluation pipelines that eliminated manual analysis steps and significantly shortened the time from measurement to prediction for customers and internal stakeholders
• Analyzed and interpreted multivariate MIR spectral data from the company’s proprietary analyzer using R and Python, supporting reliable identification and quantitation of chemical compounds in solution

• Design and implementation of DevOps and CI/CD practices for data and analytics teams
• Introduction of infrastructure as code with Terraform (IaC)
• Setup and maintenance of GCP user and permission management with Terraform in multi-project environment
• Design and implementation of CI/CD pipelines with GitHub
• Leading and training developer team for the introduction of IaC and CI/CD practices
• Building and optimising database connectors with Apache Arrow for terabyte scale data extraction (Oracle, SAP)
• Optimising data lake storage and warehouse ingest

• Implementation of specified DevOps solutions to automate infrastructure (Terraform, Bicep, CloudFormation, Ansible) on-premises datacenter (Ovirt, Proxmox, Ceph Cluster, MinIO) and private cloud.
• Administration, configuration and implementation of CI/CD DevOps pipelines (GitLab, GitFlow) to support development process (Artifactory, Prometheus, Istio, service mesh, Helm Chart, OpenShift (Red Hat Enterprise) / Kubernetes cluster), Red Hat Satellite.
• Administration, setup, monitoring and patching of Linux infrastructure based on Red Hat Enterprise for Dev, Test and QA.
• Use of Scrum and Kanban methods.
• Administration, configuration and implementation of security standards for deploying on Dev, Test, QA and Prod stages of the new ePA applications.
• Development of new plugins and add-ons needed on current infrastructure.
• Database support.
• Data analytics support (Python, Spark, Pandas, Power BI, Splunk Enterprise).
• Implementation of best practices for DevSecOps and BizDevOps using GitOps (ArgoCD), Streamlit framework, Semaphore Ansible UI.
• Configuration and testing of iperf, uperf, sysbench using benchmark-operator for external source data and IoT/MDM devices, creating reports via ELK / OpenSearch.
• Building a new Databricks platform to collect and analyze big data from different sources and IoT devices into Hadoop framework (Python, Pandas, PySpark, Power BI, Apache Airflow).
• Building backend data aggregation and processing to automate configuration deployment between different OpenShift clusters and big data framework (Python, Pandas, PySpark, Apache Spark, PostgreSQL, Django 2, Ansible Automation, Jira JSM).
• Building a new ML pipeline platform using Kubeflow, TensorFlow, KServe.
• Data extraction, transformation and loading from different data sources including structured and unstructured data to analytic DWH / big data cluster using Python, Pandas, Polars, Power BI, Django backend and PostgreSQL.
• Setup of new DevOps Test and QA HashiCorp Vault cluster for PKI and IAM.
• Configuration and testing of automated patching based on CVSS score, SIEM-integrated CVEs.
• Use of Nexpose and InsightVM to scan vulnerability events in network, host, container and application.
• Design and implementation of secure and scalable AWS architectures including VPC, EC2, S3, RDS and Route53 and similar setups on Azure and GCP.
• Automated system provisioning and deployment using CloudFormation templates.
• Configuration of IAM roles, policies and permissions to ensure secure access control.
• Patch management, backup automation and disaster recovery setup on AWS infrastructure.
• Monitoring and optimization of system performance using AWS CloudWatch and AWS Trusted Advisor.
• Support of VMware services (vSphere, Aria, Horizon) and the virtual desktop environment.
• Development and maintenance of CI/CD pipelines using Jenkins, GitLab CI/CD and AWS CodePipeline with interface to Nutanix.
• Configuration of AWS CloudWatch to monitor application performance and system events.
• Planning and execution of migration of on-premises applications to AWS cloud platforms.
• Deployment of containerized applications using Docker and Kubernetes in AWS environments.
• Deployment of internal software packages between availability zones using AWS CodeDeploy.
• Building and deploying ML models using Scikit-learn, XGBoost and Spark MLlib including hyperparameter tuning, model evaluation and production deployment.

• Architected and deployed a production-scale GraphRAG system using Neo4j, embeddings, and multi-hop reasoning over 120M+ nodes, improving answer precision by 32%, reducing hallucinations by 41%, and lowering retrieval latency by 38%.
• Designed and implemented an enterprise agent ecosystem using Model Context Protocol (MCP), exposing internal APIs, databases, and services as secure callable tools for autonomous workflows and system integration.
• Designed and deployed a production LLM-based email routing agent using Microsoft Graph API, MCP, and Azure OpenAI, achieving 96% routing accuracy, reducing manual triage workload by 65%, and decreasing response times from 18 hours to under 4 hours.
• Implemented autonomous agent self-correction pipelines using iterative feedback loops (Ralph Wiggum), enabling reliable error detection, automated remediation, and production-safe execution.
• Developed a multimodal semantic search platform using multimodal LLMs and vector embeddings, enabling semantic discovery across 250k+ image and video assets and improving search recall by 48%.

• Applied pose estimation frameworks on thermal images using infrared cameras to enhance temperature analysis and thermal comfort evaluation.
• Performed CFD simulations to analyze and visualize airflow and temperature distribution in enclosed spaces, providing data-driven insights for improving HVAC system efficiency.
• Used transfer learning to adapt pre-trained deep learning models for different tasks and datasets, improving accuracy and reducing training time.
• Handled large datasets and applied visualization techniques such as boxplots, scatter plots, and other graphical tools to identify trends, detect anomalies, and validate data accuracy.
• Built machine learning predictive models such as linear regression, logistic regression, and classification models.
• Containerized ML models and data pipelines with Docker and orchestrated scalable training and inference workflows using Kubernetes.

• Contributed to over 20 successful projects

• Working on the AnoMoB project, applying homomorphic encryption to extract insights from encrypted mobility data.
• Explored CKKS and TFHE schemes, multi-party computation, oblivious transfer, and proxy re-encryption.
• Implemented encrypted comparison and homomorphic operations on complex numbers using CKKS.
• Homomorphic encryption with OpenFHE & TFHE-rs (Rust), SQL analysis, ML (Pandas/Polars/Scikit-learn)

• AI assistant using an offline model, capable of voice recognition and real time Text-to-Speech.