AI Agents Experts in Frankfurt

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

• Functional requirements management for DIVID, the Umweltbundesamt platform for administering the single-use plastics fund. Focus: entitled parties, sub-entitled parties, and benefit reports.
• Consolidation and analysis of specifications, Jira, Confluence, functional concepts, and UX designs. Independent structuring and delimitation of requirements, as well as identification of contradictions, gaps, and dependencies.
• Creation and quality assurance of implementable user stories with clear, testable acceptance criteria. Preparation of decision alternatives and coordination with business, development, UX, and QA through team refinement.
• Conducting manual and technically assisted accessibility tests. Coordinating findings with QA and the Product Owner for further planning and implementation.
• Result: more consistent requirements, clearly defined processes and stories, and transparent open decisions. Separation of assumptions from confirmed requirements; better basis for implementation, refinements, and QA test cases.

Tools used: Jira, Confluence

• Hands-on development of AI-native product prototypes with specialized AI agents for research, requirements, business logic, UX/flow design, test case generation and quality assurance.
• Structured use and orchestration of AI agents through clearly defined roles, inputs/outputs and handover points; breaking down complex product tasks into verifiable work packages and iterative prototyping cycles.
• Establishment of human-in-the-loop quality gates to validate AI-generated results for functional correctness, consistency, completeness and feasibility; targeted rework cycles in case of deviations.
• Development of a regulatory GenAI/rules prototype for CRD VI with a structured decision flow, web UI, rule-based validation and automated test cases; iteration of the business logic through to a pilot-ready POC.
• Design of an AI-to-Action banking prototype: AI intent → consent → bank/product logic → conversion including admin console; translating the product idea into MVP scope, role model, user flows and clickable prototypes.

• Fully on-premises LLM document-examination platform for a compliance-critical banking domain: agentic LangGraph pipeline with deterministic verification, every AI judgment structured and source-anchored; ~960 automated tests, zero data egress
• GPU throughput engineering (quantized serving, speculative decoding, prefix caching): 9.5x extraction speed-up, 500+ multi-document case files per day on a single A100
• AI-native EDI/EDIFACT integration platform (~116k LOC Java 25 / Spring Boot 4, 1,900+ tests): LLM-drafted partner mappings machine-verified before go-live (DFDL conformance, field-coverage checks, dry runs), ~99.5% byte match on real customer files — replacing weeks of manual mapping per partner

• Development and optimization of the RTL+ frontend application for SmartTV and set-top box platforms with React and Next.js.
• Key role in the technical coordination of developers within the team and in coordinating implementation.
• Central interface to adjacent teams to simplify development processes and improve cross-team alignment.
• Improved frontend performance, stability, and rendering behavior on low-powered devices in a restricted runtime environment.
• Implemented a frontend testing strategy with Jest, React Testing Library, and Playwright.
• Implemented accessibility improvements according to WCAG 2.2 and WAI-ARIA.
• Integrated Didomi Consent Management as a contribution to increasing ad monetization on streaming platforms.
• Used AI-supported engineering workflows with Cursor for structured implementation, refactoring, and faster problem solving.

Technologies used: React, Next.js, TypeScript, JavaScript, GraphQL, Apollo Gateway, Zustand, Tailwind CSS, Styled Components, React Testing Library, Playwright, Jest, HTML5, CSS3, AWS Lambda, EC2, CloudFront, S3, GitLab CI/CD, NX, Cursor

• Conceptual design and implementation of modular AI assistants for sales and business processes in the Microsoft ecosystem (Agentic AI, Copilot extensions)
• Frontend architecture and development with React + TypeScript for embedded chat and assistant surfaces (streaming UI, hooks, React Query, OpenAPI clients)
• Enterprise-level agent development: reusable skill/agent library, MCP server, review and compliance gates
• LLM integration into the user experience: Anthropic (Claude), OpenAI, tool use, RAG pipelines, prompt engineering, guardrails
• Architecture and code review consulting as well as mentoring in the AI development team
• Integration with Microsoft Graph, Power Platform, and Azure services
• Technologies: React, TypeScript, Anthropic Claude, OpenAI, MCP, RAG, Microsoft Graph, Power Platform, Azure

• Built an MCP (Model Context Protocol) layer for Mwanachama's agency service, turning domain manager methods into callable AI-agent tools. This included a composite tool that builds a full organization design (org chart, goals, workflows, RACI matrix) from one specification.
• Built the chat-driven agency builder (Wakala Studio and API), where an organization describes its structure in natural language and an AI agent uses those tools to construct and modify the live design.
• Added an insights service so an organization can review AI-agent interactions and completed work. Insights from that review feed back into solution design, gated by architect and user sign-off.
• Alongside this, designed and built the platform itself: ~20 Go microservices on PostgreSQL, Flutter and React clients, deployed on Kubernetes.
• AI agents scan the platform autonomously for security gaps and run scripted tests, covering API (Postman-style) and UI testing. The rest of the work stays supervised. No rogue agents, promise.

• Responsible for the concept, planning, and implementation of the product development of GetMyInvoices 2.0 and the subcomponent InvoiceRails
• Independent work on all aspects of the project, including concept, specification in tickets, and coordination of developers
• Creation, management, and prioritization of tickets to ensure all tasks are completed on time and with high quality
• Carrying out and/or coordinating tests and ensuring the proper implementation of the developed features and functionalities
• Close collaboration with developers to clarify technical requirements and ensure the implementations match the specifications
• Regular reporting on project progress and documentation of key decisions, changes, and risks
• Taking on the subject matter lead for all topics around e-invoicing and Peppol, especially in relation to the InvoiceRails component
• Internal consulting and knowledge sharing on e-invoicing and Peppol for other teams and departments
• Tracking market trends and new developments in e-invoicing and Peppol to continuously adapt the product strategy
• Ensuring the long-term scalability and flexibility of the products for future technical and regulatory changes in the e-invoicing area

• Bootcamp Coach: "Digital Sales with AI" for neuefische GmbH
• Creation of curriculum and content for career changers seeking to start a career in digital sales
• Teaching of methods and tactics for an exhaustive tech stack:
• AI Agents Zapier and make.com
• AI Tools Midjourney, heygen, Text-Text LLMs (ChatGPT, Claude, Gemini etc.)
• Sales Software Stack: Fireflies, HubSpot, WIX, Talkwalker

• Operational implementation of the growth levers of growing E-Com brands: SEO, GEO, SEA, shop, conversion, and automation of recurring processes.
• Building and managing specialized AI agent systems that work as roles (SEO, content, conversion, Shopify engineering) instead of single prompts.
• Working either as done-for-you execution or as done-with-you setup, where the brand's team can continue working on its own afterward.
• Customers and projects include TeamTex and Original Veddel, Störtebekker, ConstructionX.
• AI workshops and enablement formats for specialist and leadership teams, plus the joint webinar series AI Vibe Club with Xentral.

• In my current position, I have end-to-end responsibility for AI products: from identifying and prioritizing use cases, developing sound business cases, AI roadmaps, and capacity and resource allocation, through to scalable implementation across countries and business areas.

• I design operating models, delivery standards, and operational concepts that ensure AI product development runs reliably and scales sustainably – always aligned with strategy, goals, capacities, and business value.

• Leading and developing interdisciplinary teams of data science and product professionals in an agile working model is a core part of my role – I currently lead a team of three employees.

• I am confident in stakeholder management at senior management level and in international structures, and translate complex technical topics into clear, business-oriented recommendations for action.

• I consider governance from the outset: I consistently align AI initiatives with regulatory requirements (including the EU AI Act), risk management, and data protection requirements.

• Coached teams in Agile methodologies and Scrum framework implementation.
• Aligned the product roadmap with business goals such as increasing bookings, improving user experience, and expanding supplier integrations.
• Collaborated with developers and third-party providers to ensure smooth API integration and end-to-end functionality.
• Created and continuously refined the product backlog with user stories, bugs, and technical improvements.
• Prioritized backlog items based on business value, revenue impact, and regulatory deadlines.
• Worked closely with backend and frontend teams to clarify dependencies and prioritize technical debt.

• Responsible for operations build-up and scaling

• Defining the global digital strategy and roadmap

• Acting as product owner for the AI applications

• Developing and maintaining strategic networks to support customers’ change

• Responsible for custom projects and change management

• Product owner for an AI native application that shortens research cycles from 2 weeks to 1-2 days

• Introduced an AI agent to optimize company and market analysis processes

• Established strategic partnerships with major data and technology incumbents

• Delivered dedicated customer projects in scope, time and budget

• Platform established and running stably; deliberately reducing my involvement to refocus on an engineering mandate in the financial sector.
• Built an own SaaS learning platform from the ground up and scaled it to over 20,000 users (over 6,000 courses sold, B2C and B2B); end-to-end ownership from development through infrastructure to operations.
• Built a lab environment that provisions an isolated Linux container per user (Docker, Traefik, Go), including automatic provisioning and a dedicated subdomain per user.
• Integrated LLM features into the product and accelerated development end-to-end with AI-assisted workflows (Claude Code, Codex); CI/CD with automated tests.