Context Engineering Experts in Germany

Remote freelance role focused on Agentic AI strategy, secure application patterns, and reusable agentic workflows for a government agency.

• Development and implementation of an open-source Agentic AI strategy for a government agency, with a focus on GDPR, security, and self-hosted solutions
• Development of reusable agentic workflows and business applications that enable non-technical employees to solve business problems independently
• Implementation of nine business applications with Single Sign-On (SSO) and Azure PostgreSQL integration on Hetzner Linux servers

Techstack: Python, Streamlit, Anthropic SDK (Claude), Azure, Linux, PostgreSQL, MS SQL, Angular

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.

Project: Defect Generation on Test-Bench Images of Metal Surfaces Environment: Automated Visual Inspection (AVI), Metallurgy & Manufacturing

• Objective & Implementation: Designed, architected, and trained Generative Adversarial Networks (Pix2PixHD / SPADE) for image-to-image transformation. Targeted generation of synthetic material defects (e.g., cracks, inclusions, scale) on rough metal surfaces under real test-bench lighting conditions for privacy-compliant and efficient dataset expansion (data augmentation).
• Technical Design: Implemented robust Generative AI and computer vision pipelines in Python and PyTorch. Used semantic segmentation approaches for mask-controlled defect synthesis and subsequent evaluation with EfficientDet object detection models.
• Business Impact: Massive dataset upscaling (10x) without time-consuming and costly physical test-bench runs, while significantly improving the detection performance of automated inspection systems.

Technologies & Skills Used: Python | PyTorch | SPADE | Pix2PixHD | EfficientDet | Machine Learning | Semantic Segmentation | Computer Vision

• SPA for automated communication of medical findings with role-based access (Sanctum)
• Server-side LLM integration (OpenRouter) with structured processing
• Automated sending via SMS/voice call (Twilio, ElevenLabs) with queue + status retry
• Full test coverage with 80+ documented test cases

Technologies: PHP, Laravel, LLM API (OpenRouter), Twilio, ElevenLabs, Laravel Sanctum, PHPUnit, Playwright, Docker, REST

Independent engineering practice focused on custom AI systems, production delivery, and fractional technical leadership.

Selected client engagement: Scalutions

• Role: Serve as fractional CTO and hands-on technical lead, responsible for the architecture and agentic infrastructure behind its managed B2B outbound operation.

• Product: Designed and built OutboundLoop, an agentic SDR operating system for research, qualification, personalized outreach, campaign management, human approvals, measurement, and continuous improvement.

• Scope: Own the full system lifecycle—from business processes and agent behavior to context design, model routing, integrations, evaluation, telemetry, reliability, cost control, and production operations.

• 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.

• Acted as technical consultant to optimize multi-layer ensemble models combining ResNet, CNN-BiGRU-Attention, and XGBoost.
• Guided implementation of a Logistic Regression meta-learner to solve class imbalance problems, achieving 92.86% accuracy and 0.9644 AUC on PTB-XL and Chapman-Shaoxing datasets.

• Built and fine-tuned CNN and RNN architectures using transfer learning for real-world classification tasks — core deep learning skills applicable to BMW's multimodal LLM and GenAI vehicle function development.
• Implemented Dropout, Batch Normalisation, and Early Stopping across deep learning experiments; evaluated rigorously using precision, recall, F1-score, and confusion matrices for production-grade reliability.
• Developed an AI-powered attendance management system using LBPH facial recognition, deployed via Flask web interface with real-time SMS notifications — demonstrating end-to-end AI product delivery for real users.
• Collaborated across cross-functional teams to deliver scalable, documented ML pipelines designed for reproducibility — matching BMW's interdisciplinary team and research environment.
• Integrated AI tooling directly into the development workflow from design through to testing, maintaining high velocity without compromising correctness.

• Co-own the architecture and development of enterprise-grade AI and backend systems spanning communication automation, embedding-based candidate matching and talent-pooling workflows; shape product and feature direction across business, compliance and technical implementation.
• Design and implement production-grade AI pipelines and multi-step LLM workflows, including orchestration, prompt and context engineering, LLM routing and assessment, and integration with internal services and business data.
• Co-own the core candidate-matching system, leveraging vector embeddings and cosine similarity within internal ingestion and attribute-derivation pipelines.
• Drive the architecture and evolution of the candidate-pooling system, including its LLM-based routing and assessment layer.

Worked as an App Engineer as part of the IoT Control team in a React Native Stack.

• Implementing new Components based on the Tonies Design System.
• Improving, extending and maintaining Tonies Design System
• Adding new features like Volume and Playback Control of the Tonies
• Fixed connection issues via bluetooth and wifi
• Removing technical debt and polishing for an upcoming big software and hardware release
• Improving accessibility by optimizing screens and components for usage via screen readers.
• Wrote lots of automated tests to ensure app quality is always stellar.
• Weekly app releases in a high volume workload environment

Results & Impact:

• Improved app stability and connection reliability ahead of a major software and hardware release
• Raised overall app quality through a significantly broader automated test suite, catching regressions before they reached users
• Made the app usable with screen readers, improving accessibility for a wider audience
• Sustained a weekly release rhythm in a high-volume production environment without quality regressions

Technologies: react-native, expo, typescript, react-19, react-compiler, react-navigation, zustand, @tanstack/react-query, i18next, figma, app-store, play-store, sentry, bitrise, config-cat, poeditor

• Impact: Arcate turns scattered customer signals into ranked product decisions for B2B product teams. Every initiative is prioritized by revenue at risk. Every decision is traceable from customer quote to board slide. Built solo, deployed in production. Model validated at Kendall's tau = 0.924 vs. senior PM judgment across 60 simulation runs.

• Skills: Artificial Intelligence, AI Agent, Large Language Model (LLM), RAG, Model Context Protocol (MCP), Agentic Workflows, Supabase, TypeScript, Deno, PHP, Stripe, PostgreSQL, Product Strategy, Positioning, GTM

• Capabilities:

• Signal Ingestion: Slack, Intercom, Gong, Salesforce, HubSpot. Signals classified by business severity to prioritize revenue-risk decisions.

• Revenue Scoring: Fermi Leverage model. Initiatives ranked by customer ARR at risk, signal strength, and multi-account confirmation.

• Roadmap Intelligence: Every bet traceable from raw customer signal to scored, board-ready decision.

• Built:

• MCP Server (v0.10.0): 12 tools, JSON-RPC 2.0, Supabase Edge Functions, SHA-256 API key authentication.

• Scoring engine: Log-scaled ARR weighting, sqrt-dampened signal strength, multi-account signal confirmation.

• Agentic Workflows: 18 automated pipelines covering release, provisioning, design QA, guard QA, and signal ingestion via Slack agents.

• AI Skills: 7 codified skills including CEO Prioritizer, Design System Enforcer, MCP QA, Simulation Runner.

• Automated QA: Browser-based screenshot validation of every screen against design tokens on every build.

• Full SaaS: Auth, billing, media pipeline, design system. Deployed solo in production.

• Stack: Supabase (Auth, DB, Edge Functions, Realtime), Stripe, Cloudinary, PHP, TypeScript, Deno

• Shifted roles from Business Analyst to Project Manager: steering delivery instead of gathering requirements.
• Led the make-or-buy decision and presented it to the Group IT management.
• Provided functional input for procurement contract negotiations, followed by sprint-based partner management.
• Evaluated the low-code platform OutSystems against the complete requirements catalog.
• Transferred the requirements catalog to Jira: ten epics, more than 140 issues, and acceptance criteria in Given-When-Then notation.
• Assessed three implementation partners.
• Implementation is progressing in sprints based on the delivered backlog.

Methods and approaches: Make-or-buy assessment, user stories with Gherkin, sprint management, migration planning

Enterprise systems: OutSystems, SAP S/4HANA, PCM, Snowflake, IBM Planning Analytics (TM1), Jira

Technologies and tools: Python, Microsoft Excel, Claude (Anthropic API)

• Consultant for system architecture, AI agents & integration, coach for data & process logic, Graph-RAG approaches, security and data protection.
• On-premise AI solutions with high compliance and performance requirements.
• Architecture decisions, operational setup, strategic prioritization & deployment.
• Technologies: LiveKit JS SDK, LiveKit Agents, Web Audio API, JS, AudioWorklet, Loki, vLLM, Zscaler, Docker, Neo4j, MySQL, Python.
• Models: GPT-OSS 20B, Whisper large v3 turbo, Qwen3-TTS.

agentic-engineer.online is my publicly testable live demo and at the same time the platform where I show my work. Originally created as a recruitment trial task, I have since continued to run it as my own demo, learning, and product project — on a Hetzner VPS behind a Cloudflare tunnel, through a multi-stage AI-orchestrated deploy pipeline with snapshot rollback. If a deploy step breaks, the system falls back to the last clean snapshot, the script is adjusted, the test repeated — empirical, test-driven, without hand tuning.

• Technically behind it: Python and FastAPI, an OpenRouter model cascade, SQLite persistence, and Cloudflare edge tuning.
• I am the developer and the strictest customer of my own AI work in one person — what started as a prototype has become a tool I use every day and against which I test my own products.