AI Engineers in Germany

• Lead AI product and design strategy for three Avitum renal-care digital products serving Europe and Asia, with launches in South Africa and South America; own the product vision, prioritization, customer discovery and success metrics for two of them
• Led the build-versus-buy decision for a new product, bringing together technical, architecture, management and marketing leads; the assessment showed that the vendor could not deliver its promised 3-6 month launch because of integration work and vendor dependencies; integrating it would have taken longer than our ~8-month build
• Wrote the ~€1.24M investment case for an in-house build, approved by senior management and the board in Sep 2026; set a December check-in for a second parallel team; set the team structure and resourcing with the Head of Digital Technology
• Lead a 3-person pod that introduced a multi-agent software delivery process with human approval gates within the existing MDR development process; the internal development team now uses it, and it is being applied to the new build
• Wrote the playbook for the process and set up a network of AI champions, giving squads one shared approach to AI-assisted delivery
• Applied agents to product-owner work, triaging tickets and compiling weekly reports
• Make go/no-go decisions on technical options based on the engineering team's assessments, and make the design decisions

Databricks Architecture & AI Data Products [Databricks Apps · Unity Catalog · Delta Lake · Lakebase · Asset Bundles · Azure DevOps · MCP]

• Designed a layered Databricks financial data architecture: Apps/FastAPI for serving, modular Python calculation engines, SQL/Delta for governed analytics, and Unity Catalog Volumes for versioned workbook outputs.
• Integrated Lakebase PostgreSQL operational data with SQL warehouse analytics, keeping transactional and analytical access separate through App service-principal identity, short-lived credentials and controlled, read-only data interfaces.
• Defined DEV/TST/PRD deployment architecture using Databricks Asset Bundles and automatic Azure DevOps CI/CD, with reusable environment configurations, OAuth M2M identities and automated application/resource lifecycle management.
• Designed access boundaries across Apps, SQL warehouses, Unity Catalog tables/functions/Volumes and secret scopes; separated deployment, application and SQL identities through declarative resource permissions and environment-specific authentication.
• Built serverless Spark pipelines for geospatial reference data and a traceable storage architecture combining immutable Volume artifacts, revision lineage and append-only Delta history with durable audit-event delivery.
• Connected AI Hub agents to governed Databricks financial workflows through typed REST/MCP interfaces; implemented CAPEX/OPEX, commercial, lease and IRR/NPV engines with scenario validation and workbook consistency checks.

• Designed and developed the central company platform LINK: tasks, CMS, shop, academy, image database, fleet records, and AI assistant in a shared data model on PostgreSQL.
• Supported the transformation of established standalone solutions into a cloud architecture; analyzed the existing data landscape and migrated it step by step.
• Integrated internal and external data sources via APIs and webhooks: Microsoft 365, shop with accounting integration, and manufacturer data.
• Implemented an AI assistant for knowledge access and document analysis, including an approval process before sending.
• Migrated and rebuilt a 49-page website with SEO in mind; launched data-driven tools (Drone Finder, Permit Finder) and lead forms.
• Served as the link between management, operations, and IT: analyzed processes on-site, translated requirements into technical solutions, and trained a team with little digital experience using real work.

Building an open-source CRM with AI integrations

Open-source CRM for small teams, offered as a cloud version and as a self-hosted core product. I own the product technically end-to-end: user interface, business logic, data model, interfaces and operations. Since December 2025, I have been working full-time on Customermates.

Responsibilities:

• Designed and built the CRM workflows for contacts, organizations, deals and tasks, with configurable table and board views.
• Frontend with Next.js, React, Tailwind CSS and MobX; backend business logic with Node.js, Prisma and PostgreSQL, input validation with Zod.
• Built a REST API, webhooks and an MCP interface that lets external applications and AI clients work directly with the CRM.
• Integrated AI assistant based on the Vercel AI SDK, with stored conversations and streamed responses.
• Developed and maintain an n8n community integration for CRM operations and event-driven automations.
• Build, delivery and operations with Docker, GitHub Actions and Vercel, both as a cloud offering and for self-hosting.

Results:

• Product live as a cloud and self-hosted version; source code and integrations public on GitHub.
• More than 200 GitHub stars for the CRM repository (as of 09/2026).

Frontend: TypeScript, React, Next.js, Tailwind CSS, MobX

Backend and data: Node.js, Prisma, PostgreSQL, Zod

APIs and AI: REST, Webhooks, MCP, Vercel AI SDK, n8n

Cloud and CI/CD: Docker, GitHub Actions, Vercel

• Led end-to-end delivery of ML/AI applications for the QuantistryLab simulation platform, from requirements definition and solution design to development, testing, deployment, and production support, coordinating efforts across back-end, DevOps, and ML teams
• Designed and implemented a compound search system with an open-weights LLM, the Pydantic AI agent framework, and the Model Context Protocol (MCP), exposing it through FastAPI endpoints
• Deployed and configured vLLM-based LLM serving on Kubernetes
• Built CI/CD pipelines and Helm charts to automate deployments across staging and production environments
• Instrumented the search system with OpenTelemetry spans and traces, integrating with the Honeycomb observability platform to monitor component-level latency and functional errors
• Developed a custom evaluation dataset and implemented evaluations for retrieval relevance, answer correctness, tool-call accuracy, and end-to-end task success
• Reduced infrared spectrum prediction time by 83% (from 60 to 10 minutes) by replacing a quantum-mechanical model with a pretrained graph neural network; fine-tuned the model using PyTorch, built and containerized the inference pipeline with Docker, and integrated it into the platform
• Implemented an MLflow model registry with MinIO-backed artifact storage
• Advised sales and science teams on ML/AI applications for prospective client projects, providing technical expertise to shape proposed solutions and prototypes

Technologies: AWS, Hetzner, Kubernetes, Helm, Docker, vLLM, Pydantic AI, MCP, Qwen, Llama 3, MLflow, MinIO, GitHub Actions, Python, FastAPI, OpenTelemetry, Honeycomb, PyTorch, Polars, pytest

Industry Software from Route to Invoice

In Production

In use at: landscaping company, two home care services

The entire workday, digital: sign-in, route plan on the vehicle, departure checks, photo documentation, time tracking, invoicing. The tablets keep working offline and sync afterward. Records are immutable, making time tracking easier to audit. Runs on a dedicated server in Germany with continuous monitoring and remote updates.

Proof: In daily use at the landscaping company with six vehicles since September 7, 2026.

• React Native on Android tablets
• Python
• SQLite
• Two-way synchronization
• Linux server in Germany
• Remote maintenance

Full overall responsibility: product, technology, compliance and go-to-market

• Delivered an enterprise MVP in 54 days, exceeding scope and schedule.
• Won a 250k € ARR anchor customer and built a sustainable enterprise sales pipeline in the first quarter.
• Paid PoCs with Zalando (35k €) and tesa (26k €), validating product-market fit with Tier-1 enterprise customers.
• Initiated ISO-27001 and TISAX certification processes. Left when the venture entered its next organizational phase.

Own company in Berlin. Building and operating our own learning platforms on Google Cloud (Frankfurt) with an AI tutor, course reports, and certificate verification. Developing AI assistants and RAG chatbots, n8n automations, and web apps with admin areas; producing learning and explainer videos in German and English.

AI Sales Teammate

• Took Halvday from concept to live product in five months, securing three design partners and two paid engagements, including PlanRadar.
• Built and shipped the product end-to-end as a solo founder, spanning product strategy, frontend, backend, agent orchestration, infrastructure, design, compliance and go-to-market.

• Taught ML, BI, and Big Data to Master's students.

Tech: Python, Power BI, SQL, ML, SnowflakeDB, databricks, MS Fabric, MongoDB, LLM

• Applied modern JavaScript features, including ES6+ syntax, destructuring, modules, array methods, and asynchronous programming, to develop efficient and readable frontend code.
• Implemented frontend integration patterns for PHP and Laravel backend services, connecting React interfaces to REST APIs and handling structured JSON data.
• Developed interactive, functional component-based frontend applications using React Hooks, JavaScript, and TypeScript, alongside backend applications and RESTful APIs using Python, Django, Flask, and FastAPI, focusing on reusable components, modular architecture, maintainability, and efficient data processing.
• Maintained a dynamic portfolio platform using PHP, Laravel, Livewire, and MySQL, implementing end-to-end functionality across frontend interfaces, backend services, and database operations.
• Validated server-side request handling, routing, middleware, and form validation using Laravel features to support reliable application workflows and consistent data processing.
• Designed and managed relational database structures using MySQL and Laravel Eloquent ORM, implementing data models, relationships, database migrations, and efficient queries for content management.
• AI-powered applications integrating Large Language Models (LLMs) through external APIs and locally hosted models, exploring practical use cases for conversational AI, intelligent automation, and AI-assisted workflows.
• Built local AI applications and developer tools for running, configuring, and interacting with locally hosted language models, gaining experience with local inference, model integration, and privacy-conscious AI workflows.
• Explored Retrieval-Augmented Generation (RAG) approaches to combine language models with external knowledge sources, enabling context-aware responses based on relevant application data and retrieved information.
• Integrated AI services with backend APIs and application components, developing reusable modules for model communication, response processing, error handling, and data exchange.

• Owned Qvantum, a cloud-based planning platform for personnel, cost center and sales planning
• Managed roadmap, prioritization and stakeholder communication
• Worked closely with development teams and business stakeholders
• Improved usability and supported data-driven decision making
• Led product development initiatives from discovery through delivery

• Architected and built an agentic creative automation platform on Mastra, with a custom RAG pipeline, custom hooks, tools and skills, Chroma for vector storage, and a MongoDB/Express backend.
• Built the agent orchestration layer powering Pixomi's multi-agent workspace, including 72 custom marketing skills, tools and hooks, and a custom context-management pipeline.
• Designed and implemented evals and observability through Mastra studio.
• Onboarded 10 pilot SMB customers producing 10x publish-ready creative output per campaign versus manual production in 3 months.
• Ran customer discovery and pilot feedback loops to shape the roadmap for an AI-native, workflow-based creation platform.

• LLM Benchmarking: Evaluated and benchmarked 1,000+ LLM-generated responses for technical correctness, code efficiency, safety, and strict adherence to complex technical prompt constraints.
• Mathematical Auditing: Executed highly granular structural audits of model-generated code and multi-step mathematical derivations, documenting root-cause logic gaps, syntax errors, and hallucinations.
• Prompt Architecture: Authored and stress-tested high-complexity mathematical, logical, and coding prompts designed to uncover edge-case failures and assess advanced reasoning capabilities.
• Model Alignment: Led RLHF and SFT workflows, utilizing Google Collab and interactive Python scripts to parse massive datasets of model outputs and deliver highly detailed preference rankings.