MATLAB Experts 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

Oracle Project Management and Automation

As part of the project, the operation of an Oracle infrastructure was automated by developing and enhancing Puppet modules and migrating existing Bash scripts to a standardized configuration management solution.

The aim of the project was to standardize and automate administrative processes, improve the maintainability of the Oracle platform, and increase the efficiency and traceability of infrastructure management through the use of Infrastructure as Code.

• Analysis and migration of existing Bash shell scripts to a Puppet-based automation solution
• Development and enhancement of Puppet modules for Oracle environments
• Automation of installation, configuration and operational processes using Infrastructure as Code
• Standardization and optimization of configuration management for Oracle systems
• Creation and maintenance of technical and operational documentation
• Planning, coordination and professional support during project implementation
• Operation and automation of Oracle systems on x86-based Linux server platforms
• Testing and quality assurance of the developed Puppet modules
• Analysis and resolution of technical errors as part of the automation and migration
• Close coordination with specialist departments and infrastructure teams to implement automation requirements

Technologies used: Puppet 7/8, SLES 15, Oracle 19, Oracle Grid, SVN, Windows Server, Confluence, VS Code, Ruby, Bash, Pass

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects

Testing and verification of high-voltage systems

• Performed integration and system tests for control units in PHEV/EV vehicles using ECU-TEST (TraceTronic), Vector CANoe, CANalyzer, ETAS INCA, Tornado, E-Sys, and EDIABAS.
• Analyzed the interaction of high-voltage control units (including CCU, BMU, inverter, IPB, and IPF) and carried out software updates and flash processes to verify new software versions.
• Worked closely with software, system, and integration teams in an agile development environment to analyze issues and verify new software versions.

• Development and maintenance of IT architectures with embedded Linux systems.
• Designing, implementing, and optimizing backend applications and script-based solutions.
• Analyzing and resolving issues, including troubleshooting and user support.
• Developing and implementing security concepts for cloud solutions.
• Administering networks (DHCP, DNS, NTP, VPN).
• Technologies: Linux, PowerShell, Bash, Python, Ansible, Kubernetes, GitLab CI.
• Methods: Kanban.

• Strategic consulting, technical consulting, interim management, and training
• Management consulting and development of application solutions through interdisciplinary solution approaches
• Employee and team development as well as innovation and communication management

• Architecture, design and development of an MVP application for a provider of specialized travel experiences
• Technologies: Python, FastAPI, Firestore, Firebase, Docker

• Executed standard/complex test cases using ECU-test and Python, improving test throughput by 30%.
• Performed validation and execution of ECU test cases on HiL benches for ADAS to ensure functional quality before release.
• Worked closely with customers to align test activities with project requirements and provide regular validation updates.
• Coordinated with subcontractors to track defects, ensure timely issue resolution, and maintain test quality.
• Ensured testbench stability and maintenance before executing test plans, identifying and resolving issues proactively.
• Developed Python-based automation scripts for reporting and workflow automation.
• Managed test issues and documentation via Jira in coordination with QA and development teams.
• Used CANPE for measuring signals of CAN, FlexRay, Ethernet, and IP using Vector CAN tools.

• Operated and teleoperated robotic systems
• Collected and labeled data for ML training
• Contributed to automation pipelines

• Development and quotation of technical solutions
• Design of high-performance solutions
• Management of aftersales operations, teams and budget
• Documentation revision

• Developed lateral-safety steering functions across two service packs, serving as Product Owner for SP-2021 and Function Developer for SP-2025
• Defined and maintained system requirements, coordinated validation and testing, and ensured seamless integration into series vehicles across 29 BMW, MINI, and Rolls-Royce models
• Drove a 62.5% reduction in Lane Keeping Assistant PPH (Problems Per Hundred) count from 9.6 (2023) to 3.6 (2025) in the US-IQS (Initial Quality Study) by enhancing function performance, contributing to a 7-position improvement in BMW’s overall brand ranking
• Managed collaboration with two main suppliers, resolving technical challenges and securing on-time milestones
• Delivered safety functions that supported multiple NCAP programs (EuroNCAP, ChinaNCAP, KoreaNCAP, JapanNCAP), with all models meeting or exceeding targets

• Designed and evaluated high-quality prompts and completions for Large Language Models (LLMs), focusing on improving response accuracy, instruction-following behavior, and factual consistency.
• Annotated and rated LLM-generated outputs for grammar, coherence, relevance, and truthfulness.
• Developed RLHF-style preference data by ranking model completions to inform reinforcement learning fine-tuning cycles.
• Participated in prompt engineering experiments to assess the effect of instruction format, verbosity, and phrasing on model behavior.
• Conducted error analysis and quality assurance on large-scale NLP datasets, identifying edge cases and linguistic ambiguity affecting LLM performance.

• Verified internal and external semiconductor technologies to support the release of design packages.
• Developed automated testing environments using Bash and Python to streamline verification workflows.
• Created and maintained TCL scripts to configure ivars and automate testbench execution.
• Performed comprehensive validation of technology libraries and Verilog files.
• Used a range of industry-standard EDA tools, including Fusion Compiler, Innovus, ICV, Calibre (Mentor Graphics), and Seascape (Ansys).
• Conducted root cause analysis to debug and resolve issues across various tool flows.
• Defined and tracked QoR (Quality of Results) metrics to provide a high-level view of design package health.
• Optimized test runtime and resource usage to improve efficiency and turnaround time.

• 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.