LaTeX Expert in Munich

• This project involved extraction of intelligence data to support report writing for a company that provides geopolitical, global, commercial intelligence. The data have been gathered from a number of resources (interview transcripts, online data, internal documents), and then a knowledge base has been build from it. This was the basis of a complex RAG system, that was evaluated against a golden dataset. Agents have been used to find out the contradicting intelligence, the statements supporting each other, and to store back the generated knowledge.

Used: Python, RAG, LangGraph, LangChain, deepeval, MCP

• Operations and extensions of Azure DevOps pipelines

• Operations and extensions of AWS services

• Citrix (Windows 10, Bitwarden)

• AWS: ECR, EKS, CloudFront CDN, Route 53, VPC peering and CNI upgrade, Atlas MongoDB, S3 buckets, static website hosting

• Azure: build and deploy with DevOps pipelines

• Introduced an integrated approach for structural damage detection across concrete, steel, and glass using advanced technologies such as LiDAR and thermal imaging. Highlighted cross-material interactions to enhance diagnostics and enable predictive maintenance.

• Developed an NLP-based medical note simplifier that transforms complex clinical instructions into plain, child-level English. Applied prompt engineering with Flan-T5 transformer models to extract patient-relevant actions and rephrase them into clear to-do items. Built dual Flask and Tornado backends with a printable web interface.

• Risk Management
• Incident Management
• Security Analysis
• Secure Coding
• Information Security Management System (ISMS)

• Developed web scraping scripts to extract and parse over 5000 product data from the Zalando website.
• Performed ETL processes using Apache Spark in CDSW, loaded the data into the Hadoop ecosystem (HDFS), and managed data using Hive and Impala.
• Implemented machine learning algorithms, achieving 85–90% accuracy on multi-class product classification.
• Integrated Zalando's product and price data into the dashboard with Otto and Takko for interactive visuals.

• Building the company with a focus on connectivity for IIoT and Industry 4.0, iRPA/process automation, advanced robotics and smart systems, sensors and services
• Project management and software architecture for IoT gateway development (since 2020) with protocol translation, IT/OT convergence and GRC
• Developing RPA bots for automating and monitoring industrial processes with an agent-based AI approach (since 2020)
• Implementing unsupervised clustering and anomaly detection for time series data in big data streaming pipelines (since 2021)
• Introducing a Docker-based release train for OTA updates with DevSecOps and CI/CD (since 2018)

• Developed and deployed custom ROS2 nodes for real-time LiDAR-IMU fusion using R3Live++ on ARM64 hardware (Docker, CMake)
• Configured IMU, camera, and LiDAR drivers for proper data timing and formats to enable real-time 3D mapping with R3Live
• Built complete simulation stack for quadrotor UAVs: Ardupilot SITL + ROS2/DDS + Gazebo Harmonic + YOLOv8 detection

• Designing and conducting Small-Angle Neutron Scattering (SANS) experiments as an integral part of nanomaterial analysis.
• Conducting training sessions, providing support, and offering advice to users on sample preparation and data analysis to ensure they utilize the instruments to their maximum potential.
• Supporting the enhancement of neutron scattering instruments to explore and characterize magnetic phenomena in novel composite materials.
• Collaborating with an interdisciplinary team to evaluate and interpret experimental results, comprehend the scientific value of measurements, and engage in discussions to draw meaningful conclusions.

• Container orchestration with Docker and Kubernetes clusters
• Operating cloud platforms like Rancher, Azure, and AWS
• Development with and use of infrastructure-as-code tools like Terraform, Kubectl, and Helm
• Analysis and use of Python, YAML, and JSON

• Simulated electrical power steering (EPS) system in Dymola
• Developed a simulation-based, system-dependent methodology employing Cauer thermal network modeling to characterize transient short-circuit failure behavior in power electronic components
• Assessed failure criticality based on system state monitoring against ISO 26262 permissible operating limits
• Experimentally validated simulation results through controlled short-circuit fault injection tests on EPS hardware, reducing the estimated Failure-In-Time (FIT) rate of the EPS system by up to 80%

• Financial management in a private equity transaction as part of the company's operational leadership.
• Operational and strategic responsibility for construction cost control for the private equity's Europe-wide real estate projects.
• Budget and cost planning.
• Weekly cash flow planning.
• Managing processes in accounting and payments.
• Overall leadership and responsibility for controlling.
• Forecasting and reporting.
• Technologies: Microsoft Excel, SAP R3.

• Defined initial system and software architecture
• Implemented application modules and hardware control layers
• Built test and mock environments to support validation
• Developed hardware drivers and low-level communication routines
• Authored technical documentation for internal and external stakeholders
• Tools: C/C++, QML, Linux, Windows, Raspberry PI, MQTT, CAN, Serial

• Participated in various annotation projects for machine learning models, contributing to the development and refinement of AI algorithms.