Model Context Protocol Experts in Berlin

• Led the end-to-end delivery of enterprise full-stack web applications by driving requirement analysis, solution design, frontend and backend development, database design, API integration, code reviews, team coordination, Agile execution, CI/CD deployments, production support, performance optimization, security implementation, and stakeholder collaboration to deliver scalable, high-quality software solutions.

• Mentor team of 6 ML platform engineers through weekly 1:1s, technical design reviews, and best practices, improving team velocity by 35% through structured sprint planning and skill development programs
• Define 2025–2026 ML platform roadmap in collaboration with Data Science, Cloud Engineering, and Product teams, prioritizing automated model governance, cost attribution systems, and multi-environment deployment strategies
• Partner with Data Science, SRE, and Product stakeholders to align ML platform capabilities with business objectives, reducing data scientist deployment friction by 60% through self-service platforms
• Architect and deliver production-grade MLOps platform supporting 50+ models in production with automated promotion pipelines, versioning, and rollback capabilities, achieving 99.5% platform uptime SLA
• Design distributed ML pipeline architecture using Metaflow and Argo Workflows (Vertex Pipelines-compatible), reducing model training time by 30% and deployment cycles from 2 weeks to 3 days through full CI/CD automation
• Build containerized ML services on Kubernetes with auto-scaling policies, resource quotas, and multi-tenancy isolation, optimizing infrastructure costs by $180K annually (25% reduction)
• Implement monitoring, alerting, and performance tracking using Prometheus, Grafana, and custom instrumentation, reducing model debugging time by 50% and establishing model performance SLOs
• Lead development of RAG-based document intelligence platform using LangChain, LangGraph, and vector databases, implementing agentic AI workflows for automated financial document processing
• Implement Infrastructure-as-Code using Terraform for reproducible environment provisioning and GitOps workflows, reducing infrastructure drift incidents by 80%
• Design role-based access control for ML platform, implement model lineage tracking, and establish audit trails for regulatory compliance aligned with enterprise IAM best practices

• Designed and deployed enterprise Retrieval-Augmented Generation (RAG) applications using LangChain, LangGraph, vector databases, embeddings, and open-source LLMs served through vLLM on GCP GPU infrastructure.
• Built agentic AI workflows using LangGraph with planning, reasoning, tool execution, persistent memory, session management, and Human-in-the-Loop approval mechanisms.
• Developed LLM-powered automation systems integrating BigQuery, SQL pipelines, and external advertising APIs including Meta, TikTok, Amazon, Snapchat, Google, and Pinterest, reducing manual operational workflows.
• Architected multi-agent AI systems for enterprise analytics and decision-support workflows, enabling autonomous task execution and intelligent data interactions.
• Implemented retrieval optimization strategies including multi-retriever architectures, semantic search, context optimization, and query improvement techniques, improving response relevance by approximately 40%.
• Engineered structured prompting strategies, function-calling schemas, and validation workflows to improve reliability of multi-step LLM applications.
• Designed scalable AI services using Python, FastAPI, Cloud Run, Pub/Sub, BigQuery, Docker, and cloud-native deployment architectures.

Enterprise AI content categorization and AI-powered web research.

• Built multi-LLM evaluation framework with annotated data
• Iterated LLM error rates based on annotated datasets
• Implemented AI-powered web research pipeline Stack: LLM, evals, OpenRouter, Python, Node.js, TypeScript, React

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.

• Lecturer for the GenAI Track at the Master School Institute of Technology
• Development of a full-stack AI application (React + Python/FastAPI) for automated supplier product import with intelligent column and category classification (4-layer hierarchical) including human-in-the-loop validation

• Context: Healthcare and laboratory teams required faster document analysis, treatment-planning support, and reliable AI workflows for MR/VR-assisted operations.
• Contribution: Built the AI healthcare platform, model/agent workflows, VR-glasses deployment platform, REST APIs, Next.js/React interfaces, and CI/CD pipelines.
• Impact: Delivered a production-ready AI product foundation that improved clinical document review, supported laboratory automation, and made VR fleet deployment manageable across environments.

Tech: TypeScript, Next.js, Node.js, React, Java, Spring Boot, Python, PyTorch, TensorFlow, Docker, PostgreSQL, OpenAPI, GitLab, GitHub Actions.

• Insurance service provider*

Challenge: Business-critical documents were processed through external OCR providers, with ongoing costs, dependency, and data privacy risks for sensitive insurance data.

Implementation:

• Architecture and production implementation of an on-premise OCR solution with full data ownership
• Methods for recognizing document structures as the basis for automated further processing
• ML-, NLP-, and LLM/VLM-based information extraction, especially from invoices and quotations

Success: Replaced external providers: full data ownership, GDPR-compliant processing, and 75% lower recurring OCR costs per year

Used technologies: Python, Docker, Microservices, FastAPI, PyTorch, Torchvision, MongoDB, MySQL

• Built a fully responsive business dashboard with dynamic job analytics visualisation and CMS-integrated content hub (articles, audio, images) with on-demand media loading. Achieved Lighthouse scores of 100 (Accessibility, SEO) and 88 (Performance) on mobile.
• Implemented pixel-perfect UI from Figma designs across 6 pages, adding scroll-triggered animations and unit tests for critical user-input components.
• Reduced code duplication by ~20% by refactoring AI-generated frontend codebase into modular, reusable components, improving long-term maintainability.
• Accelerated development by integrating AI-assisted coding workflows and Model Context Protocol (MCP) tooling, as well as independently resolved backend issues without dedicated support.
• Technologies used: Svelte (SvelteKit), Tailwind CSS, Supabase, Sanity, GSAP, Chart.js, Vitest.

• Development and maintenance of backend services for channel integrations, including email, WhatsApp, and helpdesk connections
• Further development of the broadcast and list creation system
• Bug fixing and optimization of existing features in conversation and inbox management
• Maintenance of database infrastructure and development environment

• Led engineering execution: roadmap planning, capacity alignment, risk management, dependencies, and delivery tracking.
• Consolidated multiple payroll product lines into a unified SaaS platform on Dynamics 365 Business Central, enabling scalable post-merger operations and reducing operational complexity across the portfolio.
• Restructured engineering and product teams in a remote-first setting across Germany, Austria and Poland, consisting of five cross-functional units: compliance/enabling, platform, DevOps and two stream-aligned teams with total FTE depending on phase of reorganisation.
• Rebuilt the mid-level leadership layer and mentored engineering leaders, establishing a leadership pipeline and strengthening architectural decision-making across teams for scalable growth, delivery ownership and predictability.
• Designed platform foundations and system boundaries using Team Topologies aligned structures, enabling scalable ownership, clear interfaces and parallel development across distributed teams.
• Spearheaded AI transformation by implementing AI-assisted SDLC practices using SpecKit and GitHub Actions for automated, executable specifications, while delivering agentic product capabilities by securely exposing platform data and services to AI agents and copilots via RAG-based retrieval pipelines and MCP-style extensions.
• Drove modularisation of tightly coupled legacy logic into independently deployable services, improving maintainability, testability and architectural clarity while preserving continuity through targeted, low-risk extraction rather than full rewrites.
• Established observability, CI/CD and DevOps governance as platform capabilities, increasing automated compliance gates from 25% to 75% and improving deployment cadence by 40% across 15+ product versions.
• Improved operational resilience using DORA-aligned practices (lead time ↓50%, SaaS MTTR ↓85%), strengthening reliability and reducing support overhead.
• Coordinated engineering recovery for the German payroll platform during a company-wide P0 ransomware incident; restored platform continuity within 72h, validated data integrity, and rolled out hardened runbooks and automated recovery playbooks.
• Responsible for budget compliance and cost oversight in Engineering, with limited P&L responsibility and participating in the annual COGS/OPEX/CAPEX planning cycle.

• Leading the product lifecycle for sovereign AI platform and operating system teams for enterprise & government clients and internal stakeholders (infra, solution delivery, support, revenue)
• Built and scaled the platform from a 200-user beta to a full rollout of 70K+ members at the Bundesagentur für Arbeit (BA), secured with ISO 42001 and EU AI Act compliance
• Architected the shift to a multi-tenant shared inference, increasing GPU cluster utilization from 20% to 85% and reducing infrastructure cost-to-serve by 40% for SaaS clients
• Shipped model quantization, allowing clients to run advanced LLMs on legacy hardware (A100s GPUs) instead of the H100s, saving upwards of 70% cost per enquiry
• Abstracted complex Helm configurations into a dynamic model manager, reducing the time to install or swap models by ~80%
• Killed an expensive move to build own dashboard service, pivoting to an API-first data strategy that clients can consume directly and saving €100Ks in opex and capex
• Built a safety-first agent marketplace and control plane lighthouse project for a Tier-1 bank, allowing internal teams to deploy autonomous agents within strict regulatory guardrails