Document Management System Expert in Essen

• Development and operational implementation of effective pre-sales activities for new customer acquisition
• Operational development and implementation of best-practice conversation strategies
• Process development and process optimization
• KPI measurement, regular communication
• Coaching of the sales employees and managers involved
• On-the-job telephone training with "demonstrating" in customer conversations
• On-the-job sales coaching for sales with "demonstrating" in customer conversations
• Change management of pre-sales activities

• Transition of Microsoft Azure operations to BTC AG
• Responsibility: budget of €60k
• Staff: leadership of 5 people
• Tools: Office 365, JIRA, Confluence

Conventional Paradigm Test (CPT) – AI Evaluation & LLM Research

Development of an experimental evaluation approach to examine “paradigmatic closure” in Large Language Models — that is, the question of how far LLMs can recognize the basic assumptions, values, and limits of the paradigms within which they generate answers.

Design and testing of an additional approach to classic AI benchmarks that does not primarily measure factual correctness or task performance, but instead examines a model’s ability to recognize alternative perspectives, make implicit assumptions visible, and reflect on the limits of its own answer or interpretation framework.

Focus areas: development of evaluation criteria and test questions · LLM evaluation and comparative model analysis · prompt and response analysis · qualitative classification of model answers · study of epistemic compression and value leakage · benchmark and literature research · development of structured assessment and analysis methods

As part of CPT, existing AI evaluation approaches and benchmarks were analyzed, and a minimalist test protocol was developed that classifies model answers by response patterns such as DIRECT, CLARIFY, PLURALIST, REFUSE, and META-AWARE. TruthfulQA was used as the basis for experimental application and comparison with existing reference answers.

Technologies & Methods: Large Language Models (LLMs) · Generative AI · Prompt Engineering · AI Evaluation · TruthfulQA · Benchmark Analysis · Human-in-the-Loop Evaluation · Qualitative Content Analysis · Research & Literature Review

• I carried out a software audit and architecture consulting for an existing portal software for infrastructure provisioning for a company that offers virtual reality environments.
• Role: Mentoring and consulting
• Technologies used: Java

• PRRC according to Article 15 MDR 2017/745
• Lead MDR transition for legacy products
• Communication with the notified body DQS
• Lead technical documentation
• Strategy in activities under MDR 2017/745
• Topics from the development department
• Risk management according to ISO 14971:2019
• Compliance and regulatory consulting for management/board

• Design of requirement verification based on the INVEST principle
• Implementation of the prediction model with scikit-learn and BERT
• Implementation of the web client with ReactJS and FastAPI
• Adaptation of the T5 model to improve user story generation according to the INVEST framework
• Certification of NLP and scikit-learn
• Technologies: Python, NLP, Scikit-Learn, BERT, T5, ReactJS, FastAPI, Cursor Visual Paradigm, Visual Studio, Draw.io, NSIS, vite, Electron

• Administration and enhancement of the SharePoint farm (M.Office 365)
• Migration using ShareGate
• Building a global employee portal
• Development of DMS and customer portal solutions

• Interim takeover of project management for 3 projects within a network renewal innovation program of 12 projects
• Introduced a structured project approach and set up reporting standards for the various projects within the program guidelines
• Conducted status meetings with the project teams and consolidated the results across the program