WebSockets Expert

Consulting and software for intralogistics automation (AGV/FTS) · Product lines AGVHub (independent AGV project consulting, layout editor) and OneBob (all-in-one business software for small teams)

• Designed and planned the implementation of a supervisory control system for a bakery production line (engineering customer, kick-off workshop 08/2025): three development stages, eight acceptance-ready milestones, batch traceability, AGV integration with RFID, Vue frontend.
• Discovery and requirements discussions with plant logistics and IT teams at industrial customers (life science, aviation, steel, engineering): translated supervisory control, ERP interface, and VDA 5050 requirements into architecture and requirements specification structures.
• Go-to-market automation and analytics: Bing and Meta campaigns, LLM-supported LinkedIn content pipeline, performance dashboards for partners and sales.
• Expert posts on LinkedIn about robotics and intralogistics: around 170,000 impressions across 41 posts (03 to 08/2026).

Designed and developed an Azure-based AI and data platform transforming distributed project documents into searchable, structured knowledge for an enterprise AI assistant. Combined incremental document processing, hybrid keyword/vector retrieval, knowledge graph extraction, and conversational AI for Microsoft Teams and Microsoft 365 Copilot. Implemented Python document-processing pipelines for PDF, Word, Outlook and text files; Azure Cosmos DB lifecycle management; Azure AI Search; Azure AI Foundry and Azure OpenAI; identity-aware retrieval with Microsoft Entra ID; project authorization; a TypeScript Microsoft Agents SDK agent; Pulumi infrastructure; resilient scheduling, retry and diagnostic tooling. Technology stack: Python, TypeScript, FastAPI, Pydantic, Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Cosmos DB, Blob/Table Storage, Container Apps/Jobs, Service Bus, Key Vault, Entra ID, Docker, Pulumi, pytest, Microsoft Teams and Microsoft 365 Copilot.

• 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

• Designing the audit logging framework
• Implementing APIs for developers to integrate in their codebase
• Implementing ingestion pipeline, database query layer and UI for browsing the audit events
• Improving stability and reliability of the backend system

Co-founded a software agency building custom web and cross-platform products. I owned the technical decisions across the whole portfolio and led 12 people, while carrying delivery planning, process and client relationships for 11 clients across 3 industries.

• Technical leadership: owned the technical decisions for the codebase across every project — stack, architecture, code conventions and the tooling the team worked with — and led the developers on how work got built through code reviews, pair programming and mentoring across a team ranging from junior to senior, keeping the codebase coherent as the portfolio and the team grew

• Delivery planning against the financial plan: built the company's financial plan and derived from it the billable hours each developer had to reach per month and the hours each project could absorb to stay within budget; planned capacity and scope against those figures and negotiated budgets and delivery dates directly with clients

• Client ownership: technical contact across the portfolio — requirements gathering and prioritisation, scoping and estimates, timeline communication, budget negotiation, and consistent transparency throughout delivery

• Team and people: owned the hiring and interview process end to end and took responsibility for offboarding where it was needed; designed an onboarding that got new developers productive within 1–2 days; cleared blockers daily and kept a close eye on where effort was creating value and where it was not

• Process ownership: consolidated a micro-service landscape spread over 15+ repositories into a single monorepo, cutting backend development time by ~40% and simplifying releases for 6 engineers; set up deployment pipelines with GitHub Actions and GitLab CI; ran retrospectives and turned the feedback into concrete changes; introduced AI agents into day-to-day development

• Delivered short-staffed: when the team shrank from 8 developers to 2, restructured scope, introduced AI-assisted development to hold the schedule and took on Go backend work alongside my own frontend scope

• Architecture and code: defined the architecture for every project in the portfolio — the structure the rest of the team built within — and wrote roughly 90% of the frontend code myself, from SSR applications with Next.js and Remix to cross-platform apps with Capacitor

• From zero to production: took a practice management platform — administration, inventory, integrated online shop, chat messenger — from an empty repository to production. Live in 7 markets with at least 7 more coming up, serving tens of thousands of users

• Delivery under pressure: built and shipped a replacement online shop for a Fortune 250 client in 4 days, restoring order intake while their global shops had been offline for several weeks

• Design system: built a cross-project design system used across 7 products, so new projects and features started from a shared, consistent base

• Cross-platform and real-time: built iOS and Android apps with Capacitor for a client live event with 1,000+ participants — web sockets and push notifications for real-time content, Stripe payments supporting PayPal, Apple Pay, Google Pay and cards

Key technologies: React, TypeScript, Next.js, Remix, GraphQL, ConnectRPC, Redux, Zustand, Go, Node.js, Turborepo, Nx, Capacitor, Ionic, WebSockets, Stripe, PostgreSQL, Playwright, Cypress, Vitest, Storybook, GitHub Actions, GitLab CI, Claude Code, Cursor, GitHub Copilot

• Further development and operation of a central backend service for providing vehicle inventory for international Mercedes-Benz online shops
• Further development of a reservation service for vehicles as part of the checkout process
• Design and implementation of a highly scalable end-to-end test architecture with a focus on maintainability, reusability, and a high number of automated test cases
• Development of a multi-layer test infrastructure with a strict separation of test logic and access layers
• Development of an initialization and caching architecture to significantly speed up local and CI/CD-based test runs
• Development of an AI-supported review architecture for automated evaluation and quality assurance of end-to-end tests
• Development of a dashboard for consolidated display of a vehicle context across multiple backend systems, including AI-generated summaries and compact case analyses
• Integration and further development of connections to various reservation systems via Apache Kafka and REST
• Design of new microservices and support with architecture decisions
• Risk analysis and design of microservice migrations
• Technologies: Java, Spring, Spring Boot, Gradle, Maven, Apache Kafka, REST, OpenAPI, Swagger, Github, Confluence, CI/CD, Microservices, AI, LLMs

Manufacturing intelligence platform with enterprise workflows, RAG, real-time AI assistant features, and multi-repository backend architecture.

• Built and extended production AI/backend services with Django, DRF, FastAPI, GraphQL, Celery, PostgreSQL, MySQL, Redis, and WebSockets across a modular multi-repository platform.
• Contributed to ARIS V2, a real-time manufacturing AI assistant using LangChain, LangGraph, MCP tool orchestration, planning/execution flows, OpenAI, AWS Bedrock, Qdrant, and Elasticsearch/OpenSearch-backed retrieval.
• Supported rollout expansion from ARIS V1 in 4 of 17 client production plants to ARIS V2 currently active in 13 of 17 plants, increasing real-world deployment coverage to more than 50% of the client footprint.
• Worked on document-grounded RAG functionality including ingestion, OCR, chunking, embeddings, indexing, retrieval, reranking, and grounded answer generation for industrial workflows.

Stack: Python, Django, DRF, FastAPI, LangChain, LangGraph, GraphQL, Celery, WebSockets, OpenAI, AWS Bedrock, Qdrant, Elasticsearch/OpenSearch, PostgreSQL, MySQL, Redis, Docker.

• Complete greenfield rebuild across the whole stack — built AI-native: backend in Go and NestJS, PostgreSQL (CNPG) on K3s with GitOps/Terraform; frontend on Angular 22, zoneless.
• Orchestrated coding agents (e.g. Claude Code, Cursor) across the entire lifecycle — architecture, implementation, testing, reviews, documentation — driven by Specification-Driven Development (SDD).
• “Bruno” — LLM commentator persona backed by RAG and MCP for a personality that stays consistent across all generations (match previews, post-match reports, his own virtual bets).

Angular 22 (zoneless, without Zone.js), Claude Code, Claude Code Skills, CNPG, Cursor, Design Tokens (Spec for Code), Docker, Gherkin, Git, GitLab, GitOps, Go, Google Gemini, Grafana, Hetzner Cloud, K3s, Keycloak, Kubernetes, Lighthouse, LLM Integration, Model Context Protocol (MCP), NestJS, Node.js, NPM, Playwright, PostgreSQL, Prometheus, RAG, REST, Specification-Driven Development (SDD), Structured Outputs, Terraform, TypeScript, Vitest

• 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.

• Expert-supervised AI systems for scientific reasoning, model evaluation, and research workflows.
• Built the IAS Problem Solver, an orchestrated system for difficult mathematical reasoning; it achieved 84% in one submitted answer set on the Leipzig mathematics benchmark.
• Built a resumable state-machine pipeline for research-grade mathematics benchmark generation: source selection, LLM-agent-based phenomenon discovery, task synthesis, gold-answer and certificate generation and validation, probing, repair, human feedback, and quality gates, targeting tasks that are difficult, natural, verifiable, and cost-effective.
• Current work extends this into budget-aware AI research workflows for real scientific problems with expert review.

Tech stack: Python, OpenAI/OpenRouter-compatible APIs, embeddings, RAG, SQLite.

• Founded an AI-powered scheduling and business-management SaaS for SMBs, owning technology strategy, architecture, product development, UX, billing and go-to-market execution.
• Architected and shipped a multi-tenant platform with REST APIs, RBAC, CRM, billing and notifications, powering the manager dashboard, admin console, booking experience and iOS/Android applications.
• Led and mentored 7 software engineers, 1 DevOps engineer, 1 QA engineer and 1 UX/UI designer, while remaining hands-on across backend, frontend and product delivery.
• Built AI voice and chat agents using Python/FastAPI, OpenAI and Anthropic APIs, RAG, pgvector and tool calling; integrated Twilio, Google Calendar/Meet, Stripe and Firebase.
• Owned production infrastructure and automated delivery across separate environments using Docker, Nginx, GitHub Actions and Grafana; represented the company at accelerators and international startup events.

Selected stack: Python, FastAPI, Node.js, Vue 3, React/Next.js, React Native, PostgreSQL, Redis, Docker

• Provided technical leadership for a 4-engineer team delivering 3 major client platforms in 12 months with microservices architecture and scalability solutions — 100% of scoped majors shipped ahead of schedule vs. planned milestones (baseline: prior releases often slipped 1–2 sprints).
• Ran AI model evaluation and model outputs evaluation on LLM/AI vendor APIs: safety, completeness, instruction adherence, and groundedness review before go-live; cut escaped bad outputs in AI-integrated release checklists from recurring UAT findings to near-zero on final promote.
• Drove API development and performance optimization for payment, exchange, and AI services; fail-closed error handling and payload validation reduced integration rework cycles by ~35% vs. the first AI integration pass.
• Applied software testing, testing frameworks, code quality assurance, and code refactoring with continuous integration gates; first-pass PR acceptance improved across the team and production hotfixes on AI adapters dropped noticeably after review standards landed.
• Owned DevOps practices: Docker, GitHub Actions, Jenkins-compatible pipelines, and version control workflows — cut deployment time ~50% vs. pre-automation baseline and stabilized releases across 3 client environments.
• Implemented verifier/oracle-style pass-fail checks in container sandboxes (Harbor/Terminal-Bench aligned); wrote technical documentation so failures cleared in one review cycle.
• Led cross-functional collaboration with product and client stakeholders; translated AI evaluation scores and risk findings into plain-language briefs for non-technical partners, unblocking go/no-go decisions without extra engineering meetings.
• Used agile methodologies for sprint planning and backlog ownership; mentored engineers so mid-level contributors owned AI adapter modules independently by mid-engagement.

• 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.

Development of a route planner for incident communication.

• Development of the REST API
• Set up a patch system for maintaining the routing graph
• Expansion of the testing infrastructure
• Performance and memory optimization (JMeter, JFR)

Technologies: Java 21, Spring Boot, JGraphT, Flyway, MapStruct, Caffeine, ShedLock, JMeter, Kubernetes, JFR