Semantic Search Experts in Berlin

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.

• ▶ Built real-time voice assistant (STT → LLM → TTS pipeline) benchmarking and evaluating multiple STT providers including faster-whisper and Azure Speech. achieved sub-3s latency, Groq API (Llama 3) with multi-turn memory - directly handling edge cases in dictation, names and passcode recognition.

• Led the end-to-end delivery of enterprise full-stack web applications by driving requirement analysis, solution design, frontend and backend development, database design, API integration, code reviews, team coordination, Agile execution, CI/CD deployments, production support, performance optimization, security implementation, and stakeholder collaboration to deliver scalable, high-quality software solutions.

• Acted as technical consultant to optimize multi-layer ensemble models combining ResNet, CNN-BiGRU-Attention, and XGBoost.
• Guided implementation of a Logistic Regression meta-learner to solve class imbalance problems, achieving 92.86% accuracy and 0.9644 AUC on PTB-XL and Chapman-Shaoxing datasets.

• Concept and implementation of data-heavy platforms for enterprise customers
• Design of complex AI-based interactions (chatbots, voice control, semantic search)
• Stakeholder management with more than 10 participants in cross-functional teams
• User research: interviews, usability tests, value validation
• Definition of quality metrics and execution of value analyses

Tools & methods: Figma, Adobe XD, Miro, Chat GPT, Claude | Scrum, Kanban, SAFe, Lean UX

Selected clients: VW Group, Volkswagen, BMW, Cariad, ABUS, Gieseke & Devrient, Hamburg Senate Chancellery, German Red Cross, Deutsche Bahn, Immoscout24, Relynk

• 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.

• 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.

• Own full-stack development of an AI-native enterprise platform built on TypeScript, React, Vite, tRPC, Hono, and PostgreSQL, delivering AI-powered consulting workflows to B2B clients.
• Designed and shipped a multi-agent AI system using ReAct framework and Claude skills-style workflow patterns, including an intelligent PM assistant with rich system prompts, slash commands, tool integrations, and streaming chat UI.
• Architected an LLM evaluation framework: rubric-based LLM-as-judge, golden datasets, regression testing, and automated quality gating — ensuring consistent AI output quality at scale.
• Integrated LangFuse for end-to-end LLM tracing, conversation replays, and evaluation pipelines, enabling data-driven prompt optimisation that reduced token costs and response variance.
• Built with Drizzle ORM, pgvector, and knowledge graphs for structured data access, semantic search, and relationship-aware AI reasoning across the platform.
• Led TanStack React Query migration across the application — replacing manual state management with centralised caching and automatic refetching, reducing data-fetching boilerplate significantly.
• Practiced AI-native development throughout: Claude Code, Codex, Perplexity SDK, and LLM-assisted testing across the full development lifecycle. Deployed on Vercel + Azure ACA with Biome for linting/formatting.

• Developed YourBestChance.io, an AI-powered career resilience platform that leverages advanced machine learning to provide personalized guidance and resources for users.
• Architected and implemented a Retrieval-Augmented Generation (RAG) system supporting three languages, utilizing GPT-based large language models (including OpenAI and Grok variants) integrated with specialized vector databases for efficient semantic search and similarity matching.
• Built an interactive AI chatbot powered by generative AI and RAG pipelines to deliver real-time, context-aware responses and enhance user engagement.
• Optimized data pipelines and AI infrastructure for scalability, ensuring robust performance under increasing loads and reducing latency by 50%.
• Developed comprehensive AI strategies using ML and Gen AI to create customized growth plans; analyzed company data to identify strengths, weaknesses, risks, and opportunities for AI integration.
• Defined ethical frameworks for AI deployment, assessed workforce and leadership upskilling needs, and built phased action plans (short-, mid-, and long-term) with targeted AI integration recommendations.

• Guided systematic data collection and pre-processing for the machine learning algorithms
• Defined the labeling process and implemented an interface to annotate the datasets
• Programmed a visual deep learning algorithm to detect machine pollution in live production
• Implemented data augmentation techniques to deal with machine heterogeneity
• Supplied a containerized model with API endpoints for deployment to the production machines
• Coordinated and represented a five-person project team, prepared presentations and reports

Geeks Ltd is a UK-based technology company; WordUp is its AI-driven language-learning product focused on personalized vocabulary learning and intelligent educational experiences.

• Coordinate AI product delivery across Product, Engineering, Data, Operations, and leadership, translating user needs into scoped initiatives, sequencing work, surfacing blockers, facilitating hand-offs, and communicating progress.
• Own search, recommendation, retrieval, and content-enrichment features end to end, from requirements and architecture through Python/FastAPI implementation, testing, deployment, monitoring, and rapid iteration.
• Developed low-latency retrieval, ranking, and personalization services using AWS, OpenSearch, DynamoDB, embeddings, and reusable APIs, achieving <1s latency, 22% higher engagement, and 12% higher premium conversion.
• Use AI coding assistants for codebase analysis, scaffolding, refactoring, tests, debugging, and documentation while reviewing every output for correctness, architectural fit, security, maintainability, and user value.
• Represent technical work in planning and stakeholder discussions, gather requirements first-hand, challenge priorities constructively, explain delivery trade-offs, and help teammates make outcome-focused decisions.

Industry: Publishing, media Project management for the design of a RAG-based archive indexing solution: sovereign on-prem or hybrid compute architecture for LLM and embedding operations, pipeline for transcription and automatic tagging, semantic search across audio/video holdings. Use-case assessment and make-or-buy together with editorial, archive and legal departments, taking copyright law, the Interstate Broadcasting Treaty and the AI Act into account. Differentiator: practical LLM infrastructure experience from two of my own productive platforms combined with C-level program management in regulated industries.

• Lecturer for the GenAI Track at Master School Institute of Technology
• Development of a full-stack AI application (React + Python/FastAPI) for automated supplier product imports with intelligent column and category classification (4-layer hierarchy), including human-in-the-loop validation