Cloud Native Experts in Berlin

• Designed and deployed enterprise Retrieval-Augmented Generation (RAG) applications using LangChain, LangGraph, vector databases, embeddings, and open-source LLMs served through vLLM on GCP GPU infrastructure.
• Built agentic AI workflows using LangGraph with planning, reasoning, tool execution, persistent memory, session management, and Human-in-the-Loop approval mechanisms.
• Developed LLM-powered automation systems integrating BigQuery, SQL pipelines, and external advertising APIs including Meta, TikTok, Amazon, Snapchat, Google, and Pinterest, reducing manual operational workflows.
• Architected multi-agent AI systems for enterprise analytics and decision-support workflows, enabling autonomous task execution and intelligent data interactions.
• Implemented retrieval optimization strategies including multi-retriever architectures, semantic search, context optimization, and query improvement techniques, improving response relevance by approximately 40%.
• Engineered structured prompting strategies, function-calling schemas, and validation workflows to improve reliability of multi-step LLM applications.
• Designed scalable AI services using Python, FastAPI, Cloud Run, Pub/Sub, BigQuery, Docker, and cloud-native deployment architectures.

AI Platform Backend – Senior Developer

Brought in to design and build a backend for an AI platform from scratch, including multi-provider LLM orchestration and real-time infrastructure for AI influencer personas at scale.

Tasks and responsibilities

• Architected and implemented a multi-LLM orchestration layer with Semantic Kernel to integrate GPT-4 and other providers for core platform logic and AI influencer personas, reducing model-switching overhead by abstracting provider APIs behind a single interface.
• Designed and developed a backend from scratch in C# / .NET 10, including domain modeling with DDD, a versioned RESTful API layer, and cloud infrastructure setup on Azure.
• Built a real-time chat infrastructure with Server-Sent Events (SSE), message persistence, and delivery guarantees for live operation of AI influencer personas at scale.
• Developed a media management service with integration of cloud object storage for upload and retrieval of influencer-generated content.
• Created an integration and unit test suite with data seeding for reliable regression testing across all core platform flows, significantly reducing the production error rate.

Tools and technologies: C#, .NET, ASP.NET Core, Python, TypeScript, MySQL, Semantic Kernel, EF Core, Minimal APIs, LLM Orchestration, Prompt Engineering, Agentic AI, Generative AI, AI-Assisted Engineering, Claude Code, GitHub Copilot, Google Gemini, OpenAI API, Ollama, Redis, Azure, Azure Container Apps, Azure Database for MySQL, Docker, GitHub Actions, Clean Architecture, Vertical Slice Architecture, CQRS, Domain-Driven Design, REST API, xUnit, Integration Testing, Unit Testing, Jira, Confluence, Scrum

• Led migration to GCP using Terraform, GKE, and GitOps, improving deployment consistency and scalability
• Implemented Datadog observability stack via Terraform and datadog-operator
• Established automated end-to-end tests and on-call processes, improving incident response and service reliability
• Migrated from NGINX Ingress Controller to Kubernetes Gateway API (NGINX Gateway Fabric)
• Migrated stateful services (PostgreSQL and Redis) to GCP, improving scalability and operational reliability

• Spearheaded the transformation of Telefonica Germany’s cloud journey into a self-service, automated marketplace by leading process analysis and design efforts; facilitated UX/UI collaboration and served as Scrum Master for cross-functional agile teams to ensure timely and quality delivery
• Designed, launched, and managed an enterprise-wide Learning & Development program focused on cloud-native skills, upskilling over 1,500 employees; undertook full vendor management including sourcing, tendering, contract negotiation, and ongoing partnership to ensure curriculum alignment with evolving organizational needs
• Implemented cloud migration processes aligned with corporate compliance and process governance; improved process transparency and audit readiness while reducing operational risks
• Architected and led a cross-divisional communication strategy to enhance organizational engagement; developed multiple channels including newsletters and intranet content, acting as single point of contact for all departmental communications to ensure consistency and alignment

• Designed and implemented a hybrid recommendation system (content-based + collaborative filtering)
• Built end-to-end ML pipelines including data processing, feature engineering, model training, and evaluation
• Developed RAG-based LLM systems using LangChain and vector databases for semantic search and knowledge retrieval
• Established MLOps workflows with MLflow for experiment tracking, versioning, and deployment readiness
• Implemented deep learning models (computer vision & classification) using PyTorch and TensorFlow

• Delivered AI and data science solutions, including LLM-based chatbots and data pipelines, improving operational efficiency.
• Collaborated on product features, achieving measurable impact and maintaining strong client relationships.

Tasks: Design and operation of end-to-end cloud data platforms for enterprise clients in publishing and finance, including infrastructure automation, pipeline development, monitoring, and data quality.

Activities:

• Built multi-layer data architectures on Databricks (Apache Spark, Delta Lake), BigQuery, and GCP
• Fully automated cloud infrastructure with Terraform across 3 environments (DEV/STG/PRD)
• Developed automated data pipelines with Python, dbt, and GCP services for different data sources
• Built monitoring and alerting systems for real-time platform monitoring
• Implemented data versioning and quality checks at every layer
• Designed automated test and deployment pipelines in GitLab and Bitbucket

Achievements:

• 2× production data processing capacity, reduced spike response time from minutes to ≤15 s, server errors ≈ 0
• Replaced 3,000 lines of manual configuration with a reusable automation module for 7 customer domains, configuration errors to 0
• Delivered a complete end-to-end data platform at ~€10/month infrastructure cost
• Migrated 7 database tables with 0 downstream issues
• Removed 100% exposed credentials, eliminated external vendor dependency
• Delivered integration of 3 teams in 1 sprint

• Codebase Evaluation & Problem Design: Designed and stress-tested complex software engineering problems against large open-source Python codebases (including pandas), requiring deep context acquisition and architectural understanding to produce well-scoped, realistic problem statements aligned to strict correctness guidelines.
• Agent Failure Analysis: Assessed LLM coding agent solutions for correctness and completeness, identifying meaningful failures across edge case handling, dtype behaviour, and multi-column NaN propagation logic; documented findings with precision for downstream evaluation use.
• Programmatic Test Suite Development: Authored comprehensive pytest suites to programmatically verify agent-generated solutions against defined requirements, with deliberate coverage of boundary conditions and failure modes not caught by naive implementations.
• Containerised Environment Engineering: Built and debugged Docker environments for reproducible agent execution, including git-based repository provisioning, dependency pinning with npm ci, and multi-stage Dockerfile authoring across Linux-based containers.

OpsWorker turns Kubernetes alerts into root-cause analyses, on top of the monitoring a team already runs. I lead the technical side: the agent architecture, the AWS infrastructure it runs on (fully inside EU regions), and the engineering decisions behind it, read-only in the cluster by default, human in the loop for judgment. The stack underneath: Amazon Bedrock and Bedrock AgentCore, agents built with the Strands Agents SDK, the Claude and OpenAI APIs, and the Kubernetes API.

• Context: Healthcare and laboratory teams required faster document analysis, treatment-planning support, and reliable AI workflows for MR/VR-assisted operations.
• Contribution: Built the AI healthcare platform, model/agent workflows, VR-glasses deployment platform, REST APIs, Next.js/React interfaces, and CI/CD pipelines.
• Impact: Delivered a production-ready AI product foundation that improved clinical document review, supported laboratory automation, and made VR fleet deployment manageable across environments.

Tech: TypeScript, Next.js, Node.js, React, Java, Spring Boot, Python, PyTorch, TensorFlow, Docker, PostgreSQL, OpenAPI, GitLab, GitHub Actions.

Assessment of the product, delivery, and AI organization with a realignment of operational excellence, target architecture, and AI-first operating model

Initial situation: The product and delivery organization showed structural weaknesses in efficiency, control, and collaboration. In addition, there was no clear target architecture for AI-driven product and organizational development. At leadership level, transparency about roles, responsibilities, and operational performance was limited.

Responsibility & approach:

• Analysis of the existing product, delivery, and organizational structures with regard to processes, governance, and controllability
• Evaluation of architecture and platform in terms of scalability, future readiness, and AI integration
• Development of a target picture for an AI-first product and delivery operating model
• Derivation of concrete measures to improve operational excellence and collaboration
• Sparring with the leadership team on structured organizational development

Results & impact:

• Creation of transparency around structural bottlenecks, performance, and decision logic
• Development of a target structure for a scalable AI-first product and delivery setup
• Improved decision-making ability and controllability at leadership level
• Creation of a solid foundation for downstream transformation measures
• Definition of concrete levers to improve efficiency, collaboration, and time to market

• Conducting cybersecurity readiness checks based on an in-house assessment methodology
• Analyzing the external attack surface using the Graydaxe EASM platform
• Assessing maturity levels and deriving prioritized recommendations for action

• 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

• Elevated LLM output reliability by engineering domain-specific prompts and evaluation logic, improving reasoning consistency across production language model workflows.
• Designed advanced coding benchmarks and validated solutions to strengthen training and evaluation datasets, improving model performance on technical problem-solving tasks.
• Designed and implemented automated evaluation frameworks for technical reasoning tasks; optimized LLM output reliability by 15% through rigorous prompt engineering and rubric-based benchmarking.