Google Cloud Pub/Sub 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

• Onboarded and conducted comprehensive documentation and system analysis to assess the existing data infrastructure, facilitating rapid integration and collaboration across functional data teams (modelling, processing, reporting).
• Collaboratively defined the architecture and project structure for a central data pipeline repository, including hierarchical standards, knowledge management strategies, and role-specific responsibilities, enhancing maintainability and onboarding speed.
• Evaluated and validated open-source data routing tools (Airbyte, Apache NiFi, Dragster) for ingest and sync requirements in retail analytics, including local benchmarking and error-state testing.
• Led the design and deployment of Airbyte in Kubernetes, creating customized Helm charts, securing secrets handling, and configuring Ingress with TLS and internal DNS routing, ensuring full API and UI accessibility.
• Troubleshot and resolved Ingress controller issues, iterating through multiple stages of debugging and testing, and documented setup and replication steps for scalable reuse.
• Mapped data models to ARTS standard, supporting schema alignment for ERP and reporting use cases, and coordinated review loops to align future data processing logic.
• Drafted strategic 1-pagers comparing MinIO, Pub/Sub, and routing architectures, providing technical guidance for architectural decisions and investment planning.
• Enabled secure access and authentication mechanisms, including initial evaluation for SAML integration, cluster-level configuration reviews, and service annotation improvements.

• TrendReel, production LLM agent and RAG system (Python, LangChain, OpenAI, Groq/Llama 3, Claude, FastAPI, Kubernetes, PostgreSQL).
• Designed and built a production multi-step LLM agent system: a script generation agent with a per-platform psychology database, 7 viral narrative frameworks, and structured quality scoring, switching between Claude and Groq backends in real time based on output metrics.
• Implemented multi-provider LLM routing (Claude primary, Groq/Llama 3 fallback) with priority-chain failover and quality-based provider switching, achieving 95% inference cost reduction while holding measurable quality thresholds.
• Built an advanced RAG-style retrieval pipeline with per-platform knowledge bases, semantic content matching, and structured output evaluation across 7 decision frameworks, directly analogous to multi-tenant context-based reasoning for enterprise document workflows.
• BrainyAI, adaptive AI learning platform (Python, LangChain, Groq Llama 3.3-70B, OpenAI, Next.js, Supabase, Redis).
• Integrated Groq Llama 3.3-70B with education-level-aware prompting, dynamically adjusting vocabulary depth, citation complexity, and reasoning style across four student proficiency tiers.
• Nexus Prime, multi-tenant SaaS platform for marketing and growth automation (25 modules, 99 backend routers, 153 frontend files).
• Built a 25-module, 99-router multi-tenant SaaS platform covering ad remix, affiliates, WhatsApp inbox, email, and cart recovery, serving four subscription tiers from $199 to $1,999 per month with integrated Stripe, Paystack, and Flutterwave billing.
• AI Video Surveillance Platform, multi-tenant edge and cloud computer vision system currently in active client pitch.
• Designed a multi-tenant AI video surveillance platform combining edge YOLO26 inference on NVIDIA Jetson Orin NX boxes with a central GKE cloud layer (Postgres, Pub/Sub, ClickHouse, R2, Keycloak) for event storage, dashboards, alerting, and multi-tenancy.

Lead developer of the frontend and backend systems for a web-based pre-sales tool. It is used by sales staff and engineers to configure and calculate complex measurement systems for industrial customers. Core features include a collaboration platform, a product configurator, physical feasibility checks, and a PDF generator.

TypeScript · Node.js · Nest.js · Angular · REST · MongoDB · Playwright

• Built and fine-tuned CNN and RNN architectures using transfer learning for real-world classification tasks — core deep learning skills applicable to BMW's multimodal LLM and GenAI vehicle function development.
• Implemented Dropout, Batch Normalisation, and Early Stopping across deep learning experiments; evaluated rigorously using precision, recall, F1-score, and confusion matrices for production-grade reliability.
• Developed an AI-powered attendance management system using LBPH facial recognition, deployed via Flask web interface with real-time SMS notifications — demonstrating end-to-end AI product delivery for real users.
• Collaborated across cross-functional teams to deliver scalable, documented ML pipelines designed for reproducibility — matching BMW's interdisciplinary team and research environment.
• Integrated AI tooling directly into the development workflow from design through to testing, maintaining high velocity without compromising correctness.

• 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.

• Ongoing support and further development.

• 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.

• Implementing applications with Kotlin and Ktor as microservices
• Using MongoDB in the MongoDB Atlas cloud
• Asynchronous communication of services via Google Pub/Sub
• Using Kotest and MockK for unit tests
• Developing an administration frontend with TypeScript, React and Express.js
• Provisioning environments in GCP using Terraform
• Implementing CI/CD processes with GitHub Actions
• Operating scalable production and test environments in GCP with Kubernetes, Helm and Flux CD
• Monitoring environments with Prometheus and Grafana
• Providing BI data in the Google BigQuery data warehouse

• Investigating the PoC and replacing and refining an existing cloud and IoT power plant control solution for certificate management of renewable energy plants (solar, wind, biomass, etc.) for the largest European renewable energy network operator, including examining the field IoT devices and their integration and network connections, aiming for automated PKI key management.
• Messaging with Kubernetes for large API-connected enterprise applications
• Risk and attack vector analysis, software quality & bug assessments
• Agile workload scheduling via Jira & Confluence
• Evaluation of pub/sub message streams for MQ and Kafka.
• Various tests with “best design approaches” for resilience patterns like circuit breaker designs, throughput measurement and monitoring, bulkhead governors – for robust EA design
• Integration of API management with IBM's API Connect to Kubernetes for platform-agnostic microservices API management designs. Google Apigee
• Solution health check approaches for load burst situations + remedy
• Research and evaluation of potential sub-service providers in the coordinating role as solution manager. CIS20 controls.
• DREAD and STRIDE security assessments.

• Head of overall technical integration NSC (National Secure Cloud, project with approx. 60 employees).

• Technical integration of all subprojects into one product, definition of interfaces and basic components of a cloud including hardware, technical architecture of the IABG platform.

• Development of a Cloud Management Platform (CMP) capable of creating private/mixed clouds of any complexity based on a textual description with one click or interactively.

• CMP also includes the complete hardware management lifecycle.

• Kubernetes, OpenStack and Hadoop are used as the foundation.

• The management layer includes Harbor, Gitea, Longhorn, Keycloak, Rancher and Jenkins, which are configured automatically.

• Private cloud can run any customer workloads, including a full Hadoop layer with HDFS, Spark, MapReduce, Mesos, HBase and around 20 additional ML/DL technologies.

• Hadoop worker clusters can also be installed automatically without Kubernetes on bare metal or commodity hardware.

• OpenStack with Nova, Neutron, Ironic, Swift, Cinder, Ceph.

• Development of a Java application Rudi: SOAP, REST, containers, DB.

• Technologies: Kubernetes (K3s, Rke2, Minikube, Harbor, Gitea, Jenkins, Longhorn, Keycloak, Rancher), OpenStack (Nova, Neutron, Keystone, Swift, Ceph, Cinder, Sahara, Magnum, Kayobe, Kolla, Bigrost, Ironic), Hadoop (HDFS, Ambari, Solr, Livy, Ranger, YARN, Tez, HBase, Kafka, Hive, Zookeeper, MapReduce, Spark, Oozie, Flink), virtualization (Kubernetes (K3S), VMware, Oracle), scripting (Ansible, Puppet, Juju, Shell, Groovy, Gradle, Maven).

• Involved in the full development lifecycle, including design, coding, testing, and deployment of Java-based applications.
• Built and maintained high-performance RESTful APIs and microservices, ensuring scalability and reliable data exchange.
• Practiced code reviews, used version control systems (e.g., Git), and collaborated closely with cross-functional teams to deliver robust software solutions.
• Implemented, managed, and optimized complex business logic and decision-making processes using the Drools Rules Engine, leveraging DRL (Drools Rule Language) for dynamic configuration.
• Developed software solutions for a major service provider in the healthcare insurance sector, specifically focusing on claims processing and reconciliation logic to ensure cost-effective reimbursement for health funds.

• Subject matter expert for the client on modeling and developing Camunda BPMN 2.0
• Development of new features and APIs, and coordination of tasks
• Design and development of RESTful APIs with Swagger (code first)
• Creation of target designs, high-level concepts, and requirement specifications
• Analysis and evaluation of alternative solution approaches
• Integration of external IT systems (ANUBIS, SES, ZPS) via Google GCP Pub/Sub and RESTful web services
• Pair programming, code reviews, and collaboration with API product owners
• Consulting on transforming legacy BPMN workflows and configuring Camunda BPM
• BPMN and DMN modeling and implementation in short iterations
• Operational support, bug fixing, and knowledge documentation
• Use of TDD, static code analysis with SonarQube, and integration tests
• Automation of test cases in Java and analysis of stack traces/logs on GCP-PROD
• Identification and execution of test data and documentation of test results

• Developed RAG-based AI solutions integrated with enterprise data infrastructure for high-accuracy responses.
• Optimized LLM performance, reducing latency and cost with fine-tuned AI models.
• Built NLP pipelines for summarization, entity extraction, and sentiment analysis, enhancing automation workflows.