Artificial Neural Network Experts in Germany

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.

• This project involved extraction of intelligence data to support report writing for a company that provides geopolitical, global, commercial intelligence. The data have been gathered from a number of resources (interview transcripts, online data, internal documents), and then a knowledge base has been build from it. This was the basis of a complex RAG system, that was evaluated against a golden dataset. Agents have been used to find out the contradicting intelligence, the statements supporting each other, and to store back the generated knowledge.

Used: Python, RAG, LangGraph, LangChain, deepeval, MCP

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects

• Delivered MVP-focused full-stack architecture for a health-sector client: Vite/React frontend, backend services on Google Cloud Run, and Supabase for database plus IAM/authentication.
• Supported product requirements engineering and prioritized cost-aware workload placement, implementing browser-side/edge computation where feasible before moving logic to backend services.

• 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

• Led strategic software development of fusion algorithms for precise object tracking, trajectory prediction, and environment modeling based on multimodal sensor data (e.g., camera, LiDAR, radar, GNSS, IMU)
• Developed and implemented navigation algorithms for autonomous vehicles, including path planning, obstacle avoidance, and sensor fusion of visual, inertial, and distance-based sensor sources
• Automated extraction and training processes with CI/CD
• Developed and optimized data pipelines and processes in Microsoft Azure using Apache Spark, Databricks, and PySpark
• Developed and optimized embedded software for automotive control units
• Designed latency-critical software for real-time control in robotic systems with RTOS (freeRTOS, SAFERTOS)
• Used the Vector toolchain (CANdela, DaVinci, CANoe) for configuration and diagnostics
• Optimized existing data pipelines and processes (ETL, data warehouse, SQL)
• Developed and trained machine learning models using PyTorch
• Created deep-learning-based object detection and visual SLAM algorithms, trained on combined data from camera, LiDAR, and IMU sensors
• Implemented computer vision algorithms for object detection and classification in robotic systems using OpenCV and YOLO, utilizing synchronized image and depth data
• Implemented behavior-based control systems for autonomous robots using ROS2 Behavior Trees
• Performed testing, release, and integration of sensor fusion algorithms into automotive production programs
• Ensured adherence to proper software development processes and safety standards to guarantee high data quality (MISRA, ISO 26262, ASPICE)

• 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.

• Leading AI development for aquaculture startup, optimising shellfish visual assessments with machine learning and computer vision.
• Development and systematic evaluation of ML/CV algorithms for shellfish condition and morphometrics, using Python, Pytorch and MLFlow.
• Analysis of model performance, including identification of failure modes and edge cases in production deployments.
• Design of annotation strategies and refinement of labelled datasets for computer vision tasks.
• Detailed analysis of system performance and communication of findings through publication-quality technical reports to investors and fellow R&D staff.
• Responsible for delivery of technical roadmap.

Development of AI-based and classical models for analyzing medical and patient data, including medication analyses, diagnosis analyses, forecasts, procedure analyses, dosage analyses, comorbidity analyses, prescription analyses, patient potential analyses, and referral profile analyses. Analyses in the area of Real World Evidence.

• Gathering customer requirements
• Planning the subproject
• Designing and defining KPIs
• Designing and developing models and visualizations of the results using customer dashboards
• Developing and implementing DWH adjustments
• Deriving recommendations for action

Methods, technologies: Simulation, Artificial Intelligence, Python, R, SQL, Microsoft Power BI, Amazon Web Services, Elasticsearch, PostgreSQL, Databricks, Multivariate Statistics

• 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

• Strategic consulting, technical consulting, interim management, and training
• Management consulting and development of application solutions through interdisciplinary solution approaches
• Employee and team development as well as innovation and communication management

• Developed a CNN-based pedestrian detection system using LiDAR data
• Created Python scripts for bounding boxes, dataset labeling, and data conversion
• Evaluated model performance on datasets with point clouds

Co-founded an AI-native language learning startup, defining the product vision, AI architecture and technical roadmap. Designed and built the AI and backend stack, including LLM fine-tuning pipelines, custom agentic workflows, and scalable inference infrastructure. First product currently in private beta.

End-to-end responsibility for all products - concept, architecture, development, and production operation as the sole developer; in addition, customer meetings, proposals, and marketing.

Underwriting Copilot - AI assistant for industrial insurance (in production at customer sites)

• Supports underwriters in analyzing industrial insurance submissions - in production use at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, mixed document sets.
• Two-stage evaluation and observability pipeline (code assertions + LLM-as-Judge) that makes answer quality, retrieval accuracy, and citation integrity measurable in a regression-safe way.

Kaiki Menu Analyzer - Data intelligence platform (in production at customer sites)

• Automatically captures and analyzes menu data from around 25,000 German restaurants.
• Scalable 7-container architecture (FastAPI, partitioned PostgreSQL, Redis/RQ) with LLM-supported extraction of structured data from PDF, HTML, and images.
• Full CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas - GEO platform (in production at customer sites)

• Measures brand visibility across five AI engines (ChatGPT, Gemini, Perplexity, Grok, Claude), each augmented with web search, orchestrated as a DAG workflow pipeline (Dispatcher → Sub-workflows → Scoring → Report) with fail isolation.
• 6-container deployment (FastAPI, Celery, Redis, PostgreSQL); LLM cost estimation, PDF audit report, rule-based cross-signal insights (no extra LLM cost).

Data Pipeline & Analytics Platform - competitive analysis in the automotive aftermarket

• Automated data pipeline with gap analysis algorithms and role-based access control; 230+ tests.
• Backend with FastAPI, PostgreSQL, SQLAlchemy.

Product development (actively in progress)

BankingGPT - AI assistant for complaint management in cooperative banking

• Security architecture at the core: no AI draft reaches the customer without human approval - the approval decision is in auditable code, not in the language model (monotonic: the model may escalate, never downgrade).
• Real agentic building blocks, each with its own boundary: the model chooses tools itself through an MCP server (read-only, allowlist, capped, fail-safe); sensitive cases are handed off via an open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented by me) to a separate specialist agent (securities/law), which never lowers the review requirement (pinned by test).
• Evaluation-driven over ten analysis rounds; uncovered a security flaw through independent review and blind tests that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered in the conversation, sensitive ones escalate before generation; response latency < 7 s measured (local GPU STT/TTS).

Stack & production readiness: Python, pydantic-ai, FastAPI/Celery, PostgreSQL/pgvector, FastMCP, fasta2a, Docker; multi-tenant capable (physical vector isolation per tenant), PII encrypted, OWASP-LLM reviewed, 275 tests, CI/CD; vendor-portable (Ollama / EU Cloud Vertex).

After-Sales Assistant - agentic RAG/GraphRAG assistant on public OEM manuals (automotive after-sales)

• Genuinely agentic on LangGraph: ReAct agent with four tools and conversation memory - the model decides on its own whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher - decodes warning lights), or a workshop/booking service.
• Human-in-the-Loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and gets the driver's explicit confirmation - the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as CI gate: a three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first when there is a critical warning?) blocks the pipeline; provider-agnostic (OpenAI/Azure/Anthropic), FastAPI with token streaming.

Stack: Python, LangChain/LangGraph, Chroma, Neo4j, RAGAS/DeepEval, FastAPI, Docker.