MQTT Experts in Berlin

• 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

• Own full-stack development of an AI-native enterprise platform built on TypeScript, React, Vite, tRPC, Hono, and PostgreSQL, delivering AI-powered consulting workflows to B2B clients.
• Designed and shipped a multi-agent AI system using ReAct framework and Claude skills-style workflow patterns, including an intelligent PM assistant with rich system prompts, slash commands, tool integrations, and streaming chat UI.
• Architected an LLM evaluation framework: rubric-based LLM-as-judge, golden datasets, regression testing, and automated quality gating — ensuring consistent AI output quality at scale.
• Integrated LangFuse for end-to-end LLM tracing, conversation replays, and evaluation pipelines, enabling data-driven prompt optimisation that reduced token costs and response variance.
• Built with Drizzle ORM, pgvector, and knowledge graphs for structured data access, semantic search, and relationship-aware AI reasoning across the platform.
• Led TanStack React Query migration across the application — replacing manual state management with centralised caching and automatic refetching, reducing data-fetching boilerplate significantly.
• Practiced AI-native development throughout: Claude Code, Codex, Perplexity SDK, and LLM-assisted testing across the full development lifecycle. Deployed on Vercel + Azure ACA with Biome for linting/formatting.

• Bootstrapping a CloudOps team and building a multi-cloud provider backend for a low-code Internal Developer Platform (IDP) with env zero

• Introducing user story mapping, ADRs, milestones, and backlog management

• Designing and developing core APIs, setting up CI/CD pipelines, OpenTofu/Terraform scripts

• Representing and communicating the team with third-party stakeholders (e.g. env zero)

• (Cross-)team coaching on DevOps, software design, Terraform, Golang, and agile practices

• Developed a SolidJS frontend UI for a spectrometric water analysis system on an ARM-based embedded Linux platform
• Prototyped UI in TypeScript React/Nx with LitElements and MQTT integration
• Built production UI using SolidJS, SUID, i18next, Ajv, MQTT.js, C3.js
• Refined requirements with UX team and water analysis system engineers
• Defined and documented system architecture, MQTT message formats, frontend architecture, and development setup
• Set up frontend system from scratch, implemented domain-oriented type system, UI components, and application state
• Managed MQTT pub/sub services and schema-based message validation in frontend
• Coached two junior frontend developers
• Worked in an agile remote team using JIRA, Git, and Bitbucket

• Designed and implemented embedded firmware in C/C++ for ARM-based microcontrollers and SoCs (STM32, NXP, Infineon)
• Worked across bare-metal, FreeRTOS, and Embedded Linux environments, contributing to BSP-level functionality, driver bring-up, and system integration
• Built, configured, and validated Embedded Linux systems using Yocto, including image build, boot validation, and runtime debugging
• Developed and executed unit, integration, and system-level tests, including HIL and SIL test scenarios on real hardware and simulated environments
• Created Python and Bash scripts to automate build, test execution, simulation runs, and reporting within CI/CD pipelines (Jenkins, GitLab CI)
• Designed test cases from software and system-level requirements, covering normal operation, edge cases, and failure scenarios
• Performed low-level debugging using JTAG/GDB, analyzing boot issues, timing problems, interrupts, and peripheral behavior
• Developed and validated communication interfaces including UART, SPI, I2C, CAN using logs and external measurement tools
• Used simulation and virtual test environments to validate software behavior prior to hardware availability
• Read and interpreted hardware schematics to understand signal routing, pin multiplexing, and peripheral connections
• Supported PCB design and review activities using Altium tool, assisting with component selection, pin mapping, and bring-up readiness
• Collaborated with cross-functional hardware, firmware, and system teams to clarify requirements, document assumptions, and improve overall test coverage
• Developed web interfaces using HTML, CSS, and JavaScript (ES6) and basic REST API development with Node.js
• Experience testing web applications and building UI automation frameworks using Selenium WebDriver

• Evaluated 45+ AI use cases and developed a prioritization framework for Siemens’ internal AI roadmap.
• Tested internal tools like DRIM, SiemensGPT, Microsoft Copilot; presented evaluation outcomes to stakeholders.
• Identified performance gaps and improved tool adoption by 65%.
• Supported AI knowledge-sharing initiatives, led tool onboarding sessions, and improved team AI literacy.
• Collaborated with engineering, procurement, and digital teams on tool feedback and strategy alignment.

• FPGA code conversion from AHDL to Verilog and SystemVerilog (Altera Cyclone)
• IDE: Intel Quartus Prime (Altera)
• Code simulation: QuestaSim
• Timing analysis