Multi-Agent Systems Experts in Berlin

• ▶ Built real-time voice assistant (STT → LLM → TTS pipeline) benchmarking and evaluating multiple STT providers including faster-whisper and Azure Speech. achieved sub-3s latency, Groq API (Llama 3) with multi-turn memory - directly handling edge cases in dictation, names and passcode recognition.

• Self-employed · Berlin, Germany
• Co-founded the company and own the entire technical side: product architecture, backend, frontend, infrastructure and operations.
• Designed and built the Automated Booking System (ABS) as well as the core platform and payment logic.
• Development of AI-powered SaaS products, from architecture through backend and frontend to production operation.
• Technical consulting on product architecture, data protection and permissible automation.
• Building, running and monetising my own API products for AI agents, each available as a REST interface and as an MCP server.
• Full ownership of architecture, infrastructure, billing, legal texts and go-to-market.

Built and scaled a high-performance enterprise API for real-time address validation and data quality with sub-second latency and 99.9 % availability.

Designed and integrated the solution into e-commerce, checkout, and logistics processes of leading European companies. Reduced delivery errors and shipping costs through automated data correction and precise data validation.

End-to-end responsibility for product strategy, technical architecture, software development, enterprise customers, operations, and GDPR-compliant data processing. Combined AI-native engineering workflows, Python, SQL, API integration, data quality, and workflow automation.

• Codebase Evaluation & Problem Design: Designed and stress-tested complex software engineering problems against large open-source Python codebases (including pandas), requiring deep context acquisition and architectural understanding to produce well-scoped, realistic problem statements aligned to strict correctness guidelines.
• Agent Failure Analysis: Assessed LLM coding agent solutions for correctness and completeness, identifying meaningful failures across edge case handling, dtype behaviour, and multi-column NaN propagation logic; documented findings with precision for downstream evaluation use.
• Programmatic Test Suite Development: Authored comprehensive pytest suites to programmatically verify agent-generated solutions against defined requirements, with deliberate coverage of boundary conditions and failure modes not caught by naive implementations.
• Containerised Environment Engineering: Built and debugged Docker environments for reproducible agent execution, including git-based repository provisioning, dependency pinning with npm ci, and multi-stage Dockerfile authoring across Linux-based containers.

OpsWorker turns Kubernetes alerts into root-cause analyses, on top of the monitoring a team already runs. I lead the technical side: the agent architecture, the AWS infrastructure it runs on (fully inside EU regions), and the engineering decisions behind it, read-only in the cluster by default, human in the loop for judgment. The stack underneath: Amazon Bedrock and Bedrock AgentCore, agents built with the Strands Agents SDK, the Claude and OpenAI APIs, and the Kubernetes API.

• Developed and implemented organization-wide discovery framework based on Ulwick’s Outcome-Driven Innovation; enabled 7 Product Owners to systematically identify and quantify unrealized value through shared outcome language and opportunity scoring methodology
• Transformed Product Owner role from backlog clerks to strategic experimenters; established dedicated time budget for autonomous hypothesis testing and discovery activities
• Rebuilt customer journey maps to start at actual user need (tool selection phase) instead of platform entry point; eliminated manual data aggregation work previously done by project teams
• Implemented OKR framework across 4 product teams; defined quarterly objectives with measurable key results (e.g., 40% reduction in manual integration effort, self-service adoption increase)
• Unified 3 separate platform roadmaps through cross-team dependency mapping and shared service agreements
• Supported enterprise sales cycle with ROI modeling and technical due diligence for automotive and defense customers

• Building a full-stack e-commerce product using AI-assisted development, deliberately returning to hands-on engineering to validate how AI changes software development workflows and team dynamics.
• Exploring VP Technology, Head of Engineering, and Director of Engineering opportunities where hands-on AI experience meets organisational scaling expertise.
• Open to advisory conversations on AI-augmented engineering teams, technology strategy, platform architecture, and organizational design.
• No registered business. No commercial activity.

• Attempted founding of a platform for career development and personal coaching
• Top 3 placement in the Berlin-Brandenburg business plan competition
• Conducted independent market analysis and user research
• Built a comprehensive knowledge graph for roles, skills, and experiences
• Data transformation and setting up data pipelines on Azure

• Leading the setup of Passify’s internal automation and risk management portal, connecting workflows across teams through SharePoint and Power Automate.
• Moderating retrospective workshops and creating PRDs and design tickets during PDLC.
• Supporting ISO 27001 documentation and compliance, focusing on customer support, user registration, and internal communication processes.
• Helping align design, development, and operations in a modular design cycle, ensuring each release meets both business and user needs.
• Contributing to feature planning and validation for subcontractor flows, training dashboards, and terminal portal improvements.

• Built an AI Research Assistant with RAG, LangChain, LangGraph, and OpenAI LLMs integrated with vector search; cut research time by 30%.
• Designed custom retrieval workflows with LlamaIndex, building a ReAct-style agent for dynamic chunking; improved query accuracy by 18%.
• Researched and optimized embedding strategies, reducing retrieval cost/query by 15%.
• Developed RAG evaluation frameworks using RAGAS and Langsmith with custom datasets; improved coverage by 40%.
• Fine-tuned LLMs (LLaMA 2 on Vertex AI with custom inference containers, dynamic batching, and quantization); reduced inference latency by 25%.
• Integrated AI agents in LangGraph with short-term & long-term memory (Mem0); increased task completion rate by 20%.
• Created schema-aware synthetic data generators; fine-tuned downstream models achieving +12% F1 score.