Wi-Fi Experts in Munich

Responsible for implementing and launching a group-wide transformation program in partner management using Salesforce as the central infrastructure.

Defined business requirements for partner management, focusing on roles and permissions, and developed a comprehensive roles and permissions concept.

Organized and facilitated agile workshops (feature blueprinting) with stakeholders, business analysts, and architects to capture and align requirements.

Planned, coordinated, and approved all relevant requirements for the successful rollout of partner management within the Salesforce platform.

Prioritized epics, features, user stories, and acceptance criteria to ensure alignment with the strategic objectives of the transformation program.

Ensured the acceptance of all necessary tests within the Salesforce infrastructure before product release.

Collaborated extensively with international vendors and partners in agile software development, applying Scrum and Kanban principles for continuous improvement.

Initial technical analysis of the requirements for the two applications

Creating a system concept for the interim solution and for the final solution

Creating the product vision, customer journey, and story map for the interim solution in close cooperation with subject matter experts

Building a development team

Managing dependencies and interfaces with the other applications according to Domain Driven Design principles

Creating EPICs and user stories, and maintaining the product backlog in coordination with subject matter experts and developers

Running sprint reviews with relevant stakeholders such as subject matter experts and management

Analyzing the requirements for the final solution

The interim solution was built within 8 months and was successfully used for the 2022 heating cost billing

The interim solution has since been further developed to increase automation

A technical concept for the final solution was created

Handover to two internal Product Owners is currently in progress

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.