Graph Database Experts in Germany

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

Multi-Agent Document-Generation Platform

Problem:

Turn a single prompt into a well-researched, structured and cited document, while keeping the user in control: every stage can be reviewed, corrected or revisited before the system moves on.

Architecture:

A multi-agent system orchestrated by a central controller. More than 20 specialised pydantic-ai subagents (understanding, structuring, planning, research, writing, assembly, cross-reference check, glossary, citation, reference table and more) pass results forward through a shared plan persisted in Postgres (asyncpg); a runner layer dispatches each task by name to its agent, and mechanical steps such as formatting, table of contents and list of figures are deterministic code instead of LLM calls. Provider (Anthropic or OpenAI) is a configuration setting, and responses stream over Server-Sent Events.

Hosting & Infrastructure:

Stateless container run as a Scaleway Serverless Container on a private network with managed PostgreSQL, object storage for finished documents and assets, and centralized log shipping (Loki / Scaleway Cockpit), provisioned with OpenTofu modules and deployed through GitLab CI; usage is metered per API key.

My Contribution & Key Decisions:

• Central decision controller: a satisfaction classifier turns the user's free-text feedback into a verdict (keep working, advance, cancel or revise an earlier task), and a middleware applies it to the plan. Plan progression supports jumping back to earlier tasks and re-running the stages after them.
• Research and writing fan-out: planning produces a plan from which a research-design agent generates individual research tasks and a writing-design agent generates individual writing tasks, each linked to the research it needs. Every task runs in its own dedicated agent with its own conversation history.
• Self-review and human-in-the-loop: after each step a critical-thinking agent reviews the output; the user can accept, refine, or ask questions about a critique before the plan advances.
• MCP integrations: two remote MCP servers, web search and internal document search, connected through pydantic-ai with retries and long-running tool-call timeouts. Classifier agents decide per task whether web search is needed, and a small model condenses raw search results into structured findings before they reach the writing agents.

Usage Metering:

Clients authenticate with an API key validated against a key-management service; consumption is charged in credits calculated from token usage per model plus a markup, and exhausted quota is answered with HTTP 429.

• Building up the Enterprise Architecture department. Preparing the convergence of IT / OT.
• Mapping the global business application landscape (6 countries).
• Concept for a graph model of the application landscape. Storing the results in the open-source graph database Neo4J. Various reports in the database query language CYPHER and the visualization component BLOOM. Automatic generation of IT architecture diagrams.
• Development of an application taxonomy to identify redundant applications.
• Applying Gartner's Software Portfolio Management TIME model (Tolerate, Invest, Migrate, and Eliminate) for portfolio management.
• Enterprise Architecture Governance: establishing architecture guidelines for documenting measures and decisions.
• Process modeling according to Porter (Value Chain).
• Various architecture approvals for change requests and documentation in Architecture Decision Records (ADR).
• Working on the RACI matrix for various processes.
• Working on business capabilities as preparation for a LeanIX rollout.
• Contributing to the concept for IT/OT convergence.
• Establishing architecture guidelines in a very pragmatic corporate culture. Knowledge about applications and responsibilities is spread across the world.

• Led integration process of multiple systems between development agencies in Germany and India
• Advised on SDKs, system integration, system architecture, API contract design, Salesforce, ServiceNow, and SAP.

• Developing a model-based AI where natural language is interpreted as formal relations.
• Natural language terms are not considered rigid but fluid and can be negotiated in a context so meaning resolves by iteratively specifying.
• Develops all kinds of model solutions.
• Backed by natural language and data annotation.
• Requirements to code and other solutions.

Statistical Forecasting Algorithm

• Improvement of an statistical probabilistic forecasting algorithm for sales + evaluation
• Migration from R/On-premise to Python/Snowflake
• Productionalization on Snowflake in cooperation with data engineers & DevOps

Monitoring Dashboard

• Data engineering for preparation & provisioning of necessary data/resources on Snowflake
• Development & deployment of a Streamlit dashboard in Snowflake

ML-based Probabilistic Forecasting on Vertex AI

• Development of a ML-based probabilistic forecasting algorithm from scratch
• Implementation of MLOps pipeline in Kubeflow on Google Cloud Vertex AI

Tech Stack: Python, Snowflake/Snowpark, R, Streamlit, Gitlab/Gitlab CICD, Terraform, Google Cloud, Vertex AI (aiplatform SDK, gcloud CLI, feature store, model registry, etc), kubeflow

• Development and introduction of operations processes
• Preparation of complete documentation packages (including incident management and operations support) to meet compliance requirements
• Introduction of a workshop on IaC (Infrastructure as Code)
• Technical consulting for the project security concept (ISMS)
• Installation and operation of Kubernetes clusters on AWS, on-prem, and Azure
• Hybrid cloud architecture design (on-prem, Hetzner, AWS)
• Analysis and troubleshooting of incidents and system outages
• Network adjustments for firewall rules, gateways, OpenVPN settings, and IPsec tunnels (pfSense)
• Technical consulting on Bitbucket, Jenkins, and GitLab CI/CD pipelines
• Consulting on Ansible deployments and infrastructure automation
• Consulting on building a scalable system in the cloud (AWS / Azure)
• Technologies / Tools: Ansible, Terraform, AWS, Azure, VPN, pfSense, Jenkins, Bitbucket, Kubernetes, GitLab Runner, ISMS, Golang, Prometheus, Grafana, S3, Lambda, RDS, ECS, Cognito, OIDC, Harbor, MinIO, Postgres, Redis, Keycloak, Ceph, Proxmox, CloudFormation, PostgreSQL, Flux CD, Hetzner, IONOS, Sonatype Nexus Repository, Entra ID, Dex IdP, Pulumi

• 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.

• Mentor team of 6 ML platform engineers through weekly 1:1s, technical design reviews, and best practices, improving team velocity by 35% through structured sprint planning and skill development programs
• Define 2025–2026 ML platform roadmap in collaboration with Data Science, Cloud Engineering, and Product teams, prioritizing automated model governance, cost attribution systems, and multi-environment deployment strategies
• Partner with Data Science, SRE, and Product stakeholders to align ML platform capabilities with business objectives, reducing data scientist deployment friction by 60% through self-service platforms
• Architect and deliver production-grade MLOps platform supporting 50+ models in production with automated promotion pipelines, versioning, and rollback capabilities, achieving 99.5% platform uptime SLA
• Design distributed ML pipeline architecture using Metaflow and Argo Workflows (Vertex Pipelines-compatible), reducing model training time by 30% and deployment cycles from 2 weeks to 3 days through full CI/CD automation
• Build containerized ML services on Kubernetes with auto-scaling policies, resource quotas, and multi-tenancy isolation, optimizing infrastructure costs by $180K annually (25% reduction)
• Implement monitoring, alerting, and performance tracking using Prometheus, Grafana, and custom instrumentation, reducing model debugging time by 50% and establishing model performance SLOs
• Lead development of RAG-based document intelligence platform using LangChain, LangGraph, and vector databases, implementing agentic AI workflows for automated financial document processing
• Implement Infrastructure-as-Code using Terraform for reproducible environment provisioning and GitOps workflows, reducing infrastructure drift incidents by 80%
• Design role-based access control for ML platform, implement model lineage tracking, and establish audit trails for regulatory compliance aligned with enterprise IAM best practices

• Developed and implemented organization-wide discovery framework based on Ulwick’s Outcome-Driven Innovation; enabled 7 Product Owners to systematically identify and quantify unrealized value through shared outcome language and opportunity scoring methodology
• Transformed Product Owner role from backlog clerks to strategic experimenters; established dedicated time budget for autonomous hypothesis testing and discovery activities
• Rebuilt customer journey maps to start at actual user need (tool selection phase) instead of platform entry point; eliminated manual data aggregation work previously done by project teams
• Implemented OKR framework across 4 product teams; defined quarterly objectives with measurable key results (e.g., 40% reduction in manual integration effort, self-service adoption increase)
• Unified 3 separate platform roadmaps through cross-team dependency mapping and shared service agreements
• Supported enterprise sales cycle with ROI modeling and technical due diligence for automotive and defense customers

• Designed and implemented the agent-based AI architecture for a company-wide platform to securely deploy LLM-based agents
• Designed and implemented end-to-end RAG pipelines from multiple sources: document preprocessing, chunking strategies for different document types, embeddings, retrieval with re-ranking, and robust prompt orchestration
• Developed a modular context engineering framework with skill architecture, context isolation, and dynamic resource management; human-in-the-loop control for enterprise tool integrations
• Built the CI/CD pipeline, testing strategy, tracing on the software side as well as automated LLM and agent evaluations, red team testing and tracing, and handed over to a reproducible production environment (ISO27001 and SOC2 compliant)

In this project, I support the software development of various modules of the supply chain management solution. My responsibilities include the technical implementation and optimization of collaborative SCM processes that help companies make their supply chains more efficient, transparent, and resilient. This modular software platform facilitates communication and Collaboration with suppliers is standardized and digitized, enabling seamless traceability of quality data and supplier evaluations. Technically, I focus on development with Go/Golang for scalable backend services and on the use of Kafka for real-time messaging and event processing. I design and extend GraphQL interfaces for efficient data communication between microservices and support automated build and deployment management using Docker and Gitlab CI/CD pipelines. Data is stored in the modules I work on using a PostgreSQL database.

Technical focus: Go/Golang, Kafka, GraphQL, Docker, Gitlab, CI/CD, DevOps, PostgreSQL, JIRA, Miro

• Technologies: GoLang, JavaScript, TypeScript, AWS, Terraform, Git
• Conception of AWS infrastructure and existing services
• Analysis of IAM accounts and roles
• Setup of Cost Explorer and CloudWatch monitoring
• Setup of DynamoDB and S3 persistence of collected information
• Reporting and cost calculation
• Conception of Terraform deployment

• Evaluating openDesk as MS365 alternative
• Designing AI-optimized infrastructure
• Kubernetes orchestration
• Container security advisory