Grafana Loki Experts in Germany

• 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

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.

Further development of a software solution for managing audit applications and audit notifications according to §106d SGB V for the Association of Statutory Health Insurance Physicians in Hamburg.

• Developed numerous features, optimised performance, refactored code and analysed errors
• Refactored the development container setup
• Optimised the Gitlab-CI build pipeline
• Introduced improvements to the team workflow

• Built and further developed an AWS landing zone based on Terraform / OpenTofu (multi-account structure, IAM baselines, network and security standards)
• Designed and operated platform-oriented AWS architectures to standardize infrastructure and operations processes
• Built and operated Kubernetes-based platforms (EKS) as a shared runtime environment for application teams
• Established GitOps-based deployments with Argo CD and FluxCD
• Developed and operated central CI/CD platforms (GitLab CI, GitHub Actions, Jenkins)
• Enabled development and project teams through reusable platform building blocks
• Introduced and implemented FinOps structures (AWS Cost Explorer, CUR + Athena, Infracost, Grafana dashboards)
• Built and operated central observability platforms (Prometheus, Grafana, Loki, Alertmanager, CloudWatch)

• Conducting information classification, risk management and supplier assessment workshops
• Introduction of a customer-specific information security minimum standard (based on TISAX and ISO 27001) since Apr. 2026; implementing the same standard in parallel for a second customer
• Building an ISMS according to ISO 27001 for a logistics company (approx. 160–200 MA)
• Municipal utility company (KRITIS, approx. 450 MA): independently introduced the CRISAM GRC tool and am currently expanding it to include NIS-2 areas, took over parts of the ISB support mandate, and followed up on and remediated audit findings
• Supporting customers in implementing DORA and NIS-2, including documentation for a financial institution
• Conducting and supporting audits of systems for attack detection (SzA) according to § 8a BSIG (today §§ 31, 39 BSIG)
• Creating network structure plans according to IT-SiKat
• Creating technical security concepts (logging, IAM, attack detection)

• Error analysis and fixes including performance optimization of the in-house developed platform API
• Change and incident management in day-to-day operations
• Responsible for compliance with security and compliance requirements
• Vendor management for software development and maintenance
• Planning and execution of migration of legacy services to a cloud native platform

Role in the project: project staff, implementation team

Used skills: requirements analysis, IT service and application management, IT operations, error analysis and performance optimization, software maintenance and lifecycle management

Project environment: Cloud Native Platform (Kubernetes, Crossplane, AWS, ArgoCD, Grafana)

Transmission system operator – network provisioning platform (team lead)

• Designed the saga orchestrator in Python that provisions network fabrics with rollback.
• Split IP, identity, and resource allocation into bounded contexts with their own databases and typed clients.
• Implemented data access using DDD repositories and units of work, with no SQL in the domain code.
• Required integration tests using real PostgreSQL and RabbitMQ containers, and API fuzzing for every service.
• Introduced an agent workflow where a spec starts each change and a human approves every merge.
• Rolled out OpenTelemetry auto-instrumentation through GitOps across eighteen Kubernetes clusters.
• Led incident response for stuck provisioning and recorded every outage as a post-mortem.

Languages and software used: Python, FastAPI, Pydantic v2, SQLAlchemy async, PostgreSQL, RabbitMQ, Celery, pytest, testcontainers, schemathesis, Helm, Flux CD, GitLab CI, OpenTelemetry, pi coding agent.

Software product company – datacenter simulation SaaS (backend development)

• Built the asynchronous simulation pipeline as the second-largest contributor among more than twenty team members.
• Tagged every image by commit SHA and semver in the GitHub Actions deployment workflows.
• Diagnosed the RabbitMQ memory alarm that froze every simulation and fixed the limits in the Helm chart.
• Converted the test suite to function-style pytest, with coverage reported in every pipeline.

Languages and software used: Python, FastAPI, SQLAlchemy, Alembic, Celery, RabbitMQ, Redis, PostgreSQL, S3, EKS, Helm, Keycloak, GitHub Actions, pytest, mypy, ruff, SonarQube.

Internal AI platform – model serving and telemetry

• Built the FastAPI service that deploys open-weight models on GPU tiers as OpenAI-compatible endpoints.
• Upgraded production EKS by two Kubernetes minor versions and fixed zone-bound storage faults.
• Traced every model call, including its token count, cost, and latency, through the OpenTelemetry operator.

Languages and software used: Python, FastAPI, vLLM, LangGraph, pydantic-ai, OpenAI and Anthropic APIs, EKS, Helm, Flux CD, Terraform, GitLab CI, OpenTelemetry, Grafana.

• Azure Landing Zone architecture: Design and implement a hub-spoke, multi-region-capable Azure landing zone that provides the secure, scalable and highly available foundation for autonomous driving and parking data/ML platforms.
• Compliance through Azure Policy: Enforce security and compliance standards across Azure subscriptions via Azure Policy (guardrails, deny/audit/deploy-if-not-exists), consistently achieving top-tier infrastructure security scores.
• Infrastructure-as-Code: Automate provisioning and configuration of Azure resources with Terraform and Bicep, with changes delivered through reviewed CI/CD pipelines.
• Azure Databricks and Unity Catalog: Extensive experience operating Azure Databricks with Unity Catalog for centralized data governance, access control, lineage and auditing across workspaces.
• Monitoring and observability: Built and run infrastructure monitoring and logging with Azure Monitor, Prometheus, Grafana and Loki, covering platform health, alerting, troubleshooting and capacity trends.
• Platform at scale: Architected and operate cloud data/ML platforms supporting multi-PB vehicle data ingestion and simulation; orchestrate Argo Workflow-based recompute and autolabeling services scaling to 100k+ concurrent pods on AKS.
• Reproducible ML: Established reproducible training environments with dataset versioning and provenance tracking, enabling auditing and experiment reliability.
• Operational excellence: Automated GitHub organization management and CI/CD pipelines, improving developer productivity and deployment reliability; automated recurring operational processes.
• FinOps: Developed transparent resource utilization and cost-tracking for multi-project Azure environments.
• Leadership: Technical lead for infrastructure topics, collaborating with development, DevOps and security teams; technical interviewer and recruitment panel member for scaling the engineering team.

• 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

Built and operated the entire infrastructure and observability platform for an AI agent evaluation platform on AWS/Kubernetes. Led the evolution of an AI-first cloud-native platform by building end-to-end observability, automating infrastructure and CI/CD, improving reliability and scalability, optimizing performance through data-driven engineering, and operating in an AI-native development workflow centered on rapid iteration, code review, and automation. Tech stack included Terraform, AWS, Kubernetes, Grafana, Github Actions, Python, and Cursor.

• Build and operate an end-to-end MLOps platform on Azure ML and Kubernetes (Kubeflow) for the automated deployment, monitoring, and scaling of forecasting models (including Temporal Fusion Transformer, Informer, Autoformer).
• Implement CI/CD pipelines in Azure DevOps for the full ML lifecycle – from resource provisioning (Terraform), data transformation (Hugging Face Datasets, Pandas, PyTorch, CUDA cluster) through training and evaluation to model registry and endpoint deployment.
• Integrate MLflow for experiment tracking, model versioning, performance monitoring, and automated registration in the Azure Model Registry.
• Develop and containerize PyTorch training jobs (Azure Notebook, Jupyter Notebooks) for price and time series forecasting (PFC models) with automatic rollout via Azure ML Endpoints and REST/gRPC interfaces, Docker containerization, secured with OAuth 2.0.
• Set up monitoring and alerting mechanisms (Prometheus, MLflow Metrics), log centralization, and cost monitoring.
• Automate infrastructure provisioning and model deployment using Terraform, Helm, and Azure CLI; connect to existing market data systems and event pipelines.
• Migrate existing workloads and databases (IONOS → Azure, MongoDB) with integration into central MLOps workflows and internal networks.
• Extend the platform with LLM-based tools (LangChain, LangServe) to integrate GPT-based analysis modules into existing Spring Boot services for market anomaly detection and automated reports.
• Analyze and architect a software solution to process large volumes of data efficiently (>3000 messages/sec.) (market data store).
• Spring Boot / Java 21 container development with RabbitMQ for distributing stock market data via MongoDB (Kubernetes) with fast storage of data in Redis RMaps, deduplication, forwarding messages to Read Model queues, and building Read Models for UI display in MongoDB.
• Integration of RESTHeart to create a REST API for MongoDB.
• Build an Angular frontend to simplify data queries and master data maintenance.
• Agentic coding with remote and local LLMs (Claude Sonnet, Ollama Qwen) and MCP servers.
• Develop Python scripts for transforming and cleaning incoming stock market data (Pandas, scikit-learn).

• Definition of the software architecture
• Design and development of modules
• Supporting internal employees in the learning and onboarding process
• Tools: SAP CAP / CDS, Java 21, SAP Hana, SAP Business Technology Platform (BTP)

• It is like a startup within REWE, where we have to build a new forecasting system on Google Cloud Platform from the scratch. Although, officially my role is called MLOps, my actual tasks also include development of data processing pipelines (data engineering) and data scientists tasks such as feature engineering and model trainings.
• GCP: Terraform (tofu), Vertex AI (Kubeflow), Cloud Run, IAM, Google Cloud Storage, BigQuery, Artifact Registry
• Data engineering: Snowflake as the main data warehouse, Terraform, DBT for data model implementations
• CI/CD: GitLab. We have built a CI/CD pipeline that automates deployments of new releases up to production environment
• Development of feature store and data synchronization between environments
• Data science: evaluation of different forecasting models, including CatBoost, Contextual Gamma and Random Forest; implementation of training pipelines using Kubeflow on Vertex AI; scaling and development of an event-driven interface using Kafka as a forecasting service; evaluation of MLFlow for model tracking and model registry
• Implementation of REST API using KeyCloak OAuth2 and OpenID (JWT)
• Monitoring: implementation of dashboards with Grafana, Prometheus, Mimir, Streamlit and Loki to monitor prediction metrics, GCP and Snowflake costs for pipelines, and system metrics
• Development of Copilot Agent Skills

• Operations and extensions of Azure DevOps pipelines

• Operations and extensions of AWS services

• Citrix (Windows 10, Bitwarden)

• AWS: ECR, EKS, CloudFront CDN, Route 53, VPC peering and CNI upgrade, Atlas MongoDB, S3 buckets, static website hosting

• Azure: build and deploy with DevOps pipelines