Microsoft Power Apps Experts in Munich

• Support end-to-end innovation lifecycle, from technology scouting and use case development to incubation and implementation of digital, automation, and AI solutions.
• Designed and implemented process automation solutions using Power Automate, Mendix, and Power Apps to digitalize internal workflows and reduce manual effort.
• Prototyped AI-based agents to automate internal processes and explore efficiency gains in IT operations.
• Developed Power BI dashboards to provide leadership with clear visibility into strategic KPIs and operational performance.

• Responsibility for daily HR operations across 4 studios in Germany, focusing on personnel administration and the employee lifecycle
• Drafting, reviewing, and managing all employment law documents (employment contracts, contract amendments, certificates, references)
• Preparing payroll, especially for hourly wage models, including data preparation and coordination
• Maintaining and managing timekeeping data in the system (Gfos) and ensuring data quality
• Proactively managing and tracking personnel-related deadlines (e.g., probation periods, fixed-term contracts, evaluations) in close coordination with studio managers
• Acting as the central point of contact and reminder for managers on all HR-related topics and processes
• Structuring and tracking HR processes while ensuring completeness and compliance of all documents
• Creating and maintaining HR documents, reports, and overviews in Word and Excel

• Support and further development of a complex process for creating XML documents for electronic invoices / E-Invoicing (XRechnung, ZUGFeRD)
• Automation of operational processes, process development and optimization
• Development of frontend applications with MS Power Apps
• Porting SQL Server 2016 to SQL Server 2022
• SQL Server database administration

• Running team development measures to improve collaboration and resolve conflicts within the individual teams
• Capturing and optimizing processes, value streams and customer journeys
• Creating transparency in data and information flows
• Coaching emp...

• Developed an end-to-end AI pipeline for analyzing 2D exploded-view drawings using computer vision and deep learning models.
• Integrated YOLO-based object detection (Bounding Boxes, Post-Processing, Overlap Handling) for accurate part and callout detection.
• Applied the Segment Anything Model (SAM) for fine-grained segmentation and separation of individual components.
• Implemented OCR and feature extraction modules, and compared Vision Language Models (VLM) and traditional computer vision approaches in terms of accuracy, runtime, and scalability.

• Creation of the profit center report and statistical metrics report
• Gathering and analysis of requirements regarding the forecast for revenue and costs
• Implementation of various time series analyses and optimization of forecasts
• SAP process knowledge, SQL, Python
• Python with various libraries for time series analysis and Machine Learning

• Implemented portfolio management for small and medium projects with Planner Premium
• Developed organizational and technical standards for project management
• Automated processes with Power Automate
• Developed a Power Apps platform (interface between MS Dynamics and Planner Premium)
• Created comprehensive reporting with Power BI and MS Loop
• Area: PMO

• Architected an agentic, real-time offer orchestration engine where specialized agents (retrieval, pricing/optimization, and policy/guardrails) coordinate to personalise promotions across customer touchpoints using RAG with FAISS over Delta Lake and low-latency Databricks Model Serving. Collaborated with product managers and commercial stakeholders to shape the roadmap and evaluate emerging agent patterns for production.

• Designed an agent-based data quality service that orchestrates schema detection, entity normalization, and validator/exception-handling agents to clean multi-retailer SKU feeds at scale. Wrapped model calls in PySpark UDFs for distributed inference, automated via Databricks Workflows and CI/CD.

• Developed a multimodal, agentic extraction pipeline where vision, parsing, and compliance agents collaborate to derive brand, packaging, and volume from scanned images using Claude 3 Sonnet with Swin Transformer encoders. Orchestrated via Azure Event Hub with outputs persisted to Delta Lake.

• Implemented a GS1 taxonomy classification service built around cooperating agents for inference, drift monitoring, and auto-retraining governance using Falcon 180B (LoRA-tuned) with a batch pipeline on Databricks.

• Created a hybrid agent workflow where a retrieval agent surfaces candidate matches via embeddings and a reasoning/verification agent (Mixtral 8x7B) adjudicates receipt-to-SKU alignment, integrated into a streaming Databricks pipeline.

• Built a multimodal attribute inference pipeline structured as cooperating vision-language, rules/consistency, and compliance agents to fill NutriScore, nutrition fields, and packaging types from names and images using LLaMA 3-8B with CLIP embeddings.

• Developed a GenAI-powered orchestration system that ingests recipes from multiple websites, parses ingredients through structured extraction agents, and dynamically links them to real-time retailer offers via tagging, semantic reasoning, and business-rule agents.

• Business analysis and process optimization, including specifying business requirements and technical design
• Interface analysis (REST API, SOAP) and process optimization
• Process optimization with RPA, Power Automate, Microsoft Fabric, Power Automate Cloud, and Power BI
• Development of Power Apps for a point-of-sale platform using Power Automate and MS Fabric/Power BI to replace various tools
• Automation and replacement of manual maintenance of Excel spreadsheets and manual processes

As part of an in-house development project, a pipeline for automated lead generation was created as the second stage of a preceding system for project monitoring. Based on a list of freelance project URLs (freelancermap), qualified lead records are generated, including company, contact person, official and personal email address, and the appropriate form of address (informal/formal). The technologies used were Python (openpyxl, requests) as well as an LLM agent workflow in VS Code (GitHub Copilot Chat) with a custom slash command and extensive rule set; search APIs (Serper.dev) are connected for research. My tasks included the full concept and development. The core is a rule set of around 480 lines that guides the LLM agent deterministically through extraction, website and email lookup, duplicate matching (against existing provider lists), and the creation of a structured JSON output. Deterministic steps (Excel matching, web/email search, pattern derivation) were moved into Python helper scripts. Other requirements included validating the results through versioned blind runs against a reference, iterative refinement of the rule set, and a swappable search provider layer for cost and stability reasons.