Chroma Experts in Germany

• Marketing Strategy: Lead the end-to-end analysis and evaluation of cross-channel marketing campaigns across the entire Customer Journey. My focus is identifying optimization potential and deriving clear, actionable recommendations that drive measurable business impact.
• Data Science & AI: Advanced predictive modeling (Churn, LTV), market basket analysis, clustering, and real-time AI-powered audience discovery utilizing RAG/LLMs.
• Marketing Analytics & Measurement: End-to-end attribution analysis, Marketing Mix Modeling (MMM), audience segmentation, conversion path analysis, and A/B testing across all major platforms.
• Data Engineering & Reporting: Designing and managing robust, multi-platform data pipelines (BigQuery, GCP) for data consolidation, automated dashboard generation, and critical API integrations.

• Led integration process of multiple systems between development agencies in Germany and India
• Advised on SDKs, system integration, system architecture, API contract design, Salesforce, ServiceNow, and SAP.

• Fine-tuned and evaluated alternative backbone architectures for the AFFGAN handwriting style encoder to better capture writer-specific features, benchmarking against the original baseline architecture and replacing the legacy VGG19 architecture with a custom Transformer-based encoder.
• Extended the system beyond word-level synthesis to line-level handwriting generation, integrating and adapting an existing line-generation architecture to support full-sentence output.
• Deployed the handwriting generation pipeline as a web application, enabling users to select a writing style, input custom text, and instantly generate a corresponding handwriting image.
• Integrated TrOCR into a teacher–student distillation framework to evaluate and improve readability of generated handwriting, improving OCR accuracy by 20% over the baseline.
• Boosted user-study pick-rates by 40%, demonstrating a significant leap in the perceptual quality and realism of the generated handwriting compared to the baseline model.

Tech: PyTorch, Python, GANs, CNN, ViT, TrOCR, Streamlit, CUDA.

• Architected and built an agentic creative automation platform on Mastra, with a custom RAG pipeline, custom hooks, tools and skills, Chroma for vector storage, and a MongoDB/Express backend.
• Built the agent orchestration layer powering Pixomi's multi-agent workspace, including 72 custom marketing skills, tools and hooks, and a custom context-management pipeline.
• Designed and implemented evals and observability through Mastra studio.
• Onboarded 10 pilot SMB customers producing 10x publish-ready creative output per campaign versus manual production in 3 months.
• Ran customer discovery and pilot feedback loops to shape the roadmap for an AI-native, workflow-based creation platform.

• 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.

Designed and developed an AI-powered automation platform using n8n to analyze social media niches, identify target audiences, and automate marketing strategy generation. The solution combined AI agents, workflow orchestration, and data analysis to automate research processes and generate data-driven insights.

• Designed and implemented complex automation workflows using n8n
• Developed AI-powered analysis agents for market and audience research
• Integrated multiple APIs and AI services into automated workflows
• Built automated market, competitor, and target audience analysis pipelines
• Leveraged Large Language Models (LLMs) for information summarization, classification, and prioritization
• Containerized and deployed the platform using Docker

Technologies: n8n, AI Agents, OpenAI APIs, Prompt Engineering, LLMs, Docker, Linux, REST APIs, Webhooks

• 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

Conducted an independent technical assessment of an AI-enabled software platform, combining AI risk auditing, cybersecurity analysis and software architecture review. Reviewed application components, APIs, data flows, LLM integrations, retrieval-augmented generation, multi-agent orchestration, authentication, tenant isolation, dependency vulnerabilities, AI governance and model lifecycle controls. Authored a technical audit report with a structured risk register, source-code evidence, regulatory references, corrective actions, AI system inventory, risk classification, remediation roadmap and Key Risk Indicators.

Technologies: TypeScript, JavaScript, React, Next.js, Node.js, REST APIs, MongoDB, Redis, AWS serverless services, OAuth 2.0 / OpenID Connect, LLM APIs, RAG, vector search, multi-agent orchestration, Model Context Protocol, C4 architecture modelling, threat modelling, NIST AI RMF, ISO/IEC 42001, ISO/IEC 23894, OWASP guidance, MITRE ATLAS

End-to-end responsibility for all products – conception, architecture, development, and production operations as the sole developer; also customer discussions, proposals, and marketing.

Underwriting Copilot – AI assistant for industrial insurance (in production with a customer)

• Supports underwriters in analyzing industrial insurance submissions – in production at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, heterogeneous document collections.
• 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 with a customer)

• Automatically collects and analyzes food 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.
• Complete CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas – GEO platform (in production with a customer)

• 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 additional LLM effort).

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 development)

BankingGPT – AI assistant for complaint management in cooperative banking

• Security architecture at its core: no AI draft reaches the customer without human approval – the approval decision is stored in auditable code, not in the language model (monotonic: the model may increase the level, but never lower it).
• Genuine agentic components, each with its own boundaries: the model selects tools itself through an MCP server (read-only, allowlisted, capped, fail-safe); sensitive cases are sent via the open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented independently) to a standalone specialist agent (securities/law), which never lowers the review requirement (pinned by tests).
• Evaluation-driven across ten analysis rounds; an independent review and blind tests uncovered a security defect that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered during the conversation, while sensitive cases are escalated before generation; measured response latency < 7 s (local GPU STT/TTS).

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

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

• Genuinely agentic with LangGraph: ReAct agent with four tools and conversation memory – the model decides itself whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher – decoding warning lights), or a workshop/booking service.
• Human-in-the-loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and obtains the driver's explicit confirmation – the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as a CI gate: three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first in the case of 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.

• Delivered 40+ AI projects and 23 strategic consultations for international clients (US, Europe, Middle East), achieving a 98% job success rate and building long-term partnerships.
• Developed and deployed production-grade AI solutions in computer vision, NLP, deep learning, and generative AI (LLMs, RAG pipelines, Stable Diffusion, OCR, chatbots), enabling automation and improving client efficiency by up to 70%.
• Designed and fine-tuned large language models (LLMs), including prompt engineering and integration with enterprise knowledge bases, leading to smarter decision-making and reduced manual effort.
• Built real-time computer vision applications (detection, segmentation, OCR) and integrated them into business systems, significantly enhancing accuracy and scalability.
• Consulted startups and enterprises on AI strategy, architecture, and deployment (cloud & on-premise), accelerating product development and reducing time-to-market.
• Managed complete AI project lifecycles (requirements gathering, solution design, deployment, support) in agile, international, and cross-functional environments, ensuring high-quality delivery.

• Lead a cross-functional squad of backend, frontend, and ML/data engineers, balancing hands-on contribution (architecture, coding, reviews) with team leadership (mentoring, backlog prioritization, roadmap alignment).
• Designed and delivered ML-powered search and discovery features, including Learning-to-Rank (LTR), query expansion, and vector search, improving result relevance and user engagement.
• Implemented personalization and recommendation pipelines, using behavioral data and segmentation to increase customer retention and lifetime value.
• Established data-driven practices, building A/B testing and experimentation workflows (Odyn, MLflow) to measure feature impact on CTR, NDCG, and conversion.
• Owned the squad’s architecture and delivery roadmap, modernizing services with cloud-native microservices and event-driven systems (AWS, Pulumi, Terraform) to improve scalability and reliability.
• Improved reliability and operational excellence, introducing observability (Prometheus, Grafana, NewRelic), incident management, and postmortems that reduced downtime for customer-facing services.
• Mentored and supported engineers, fostering technical growth, collaboration, and a customer-first mindset through regular feedback, coaching, and code reviews.
• Worked closely with product managers, researchers, and business stakeholders to translate customer insights into technical solutions that improved discovery, engagement, and retention.
• Explored Generative AI/LLM use cases (GPT-4, LangChain, RAG), prototyping intelligent assistants and personalized discovery workflows that increased user satisfaction.
• Delivered tangible results: boosted engagement through personalization, contributed to revenue uplift, and reduced incidents by embedding resilience and observability.

• New development of project room functions
• Connection of REST API of a self-developed web service (.NET 7/8) as Azure App Service
• UI tests with Playwright
• Extension of Azure DevOps pipelines
• Migration to Azure SQL Server
• Software / technology: SharePoint Online, PowerShell scripts, SharePoint Framework, MobX, C#, Logic Apps, Playwright, Azure SQL Server, Graph API

• Completed an intensive AI Engineering Program focused on LLM evaluation, retrieval, agent orchestration, and multimodal workflows.
• Designed retrieval pipelines with document ingestion, semantic search, and citation-aware outputs using LangChain and ChromaDB.
• Built LangGraph-based agent workflows with state handling, clarification loops, and human-in-the-loop approval steps.
• Applied prompt engineering and evaluation patterns, including scoring logic and guardrails, to improve output quality and reliability.
• Worked extensively with Python, FastAPI, OpenAI APIs, LangChain, LangGraph, and ChromaDB in end-to-end implementations.

• Automating Software Development with Generative AI (Master Thesis): Architected a gen-AI prototype using agentic workflows, LLMs, and RAG, achieving €100,000 in annual savings by cutting development cycles by 60–80%. Collaborated with cross-functional teams to automate the software lifecycle, boosting operational efficiency by over 60%.
• Development of an AUTOSAR AI-Based Chatbot: Implemented an AI-based chatbot using NLP, vector databases, and RAG pipeline, enhancing documentation retrieval efficiency via REST APIs by 80%. Presented findings to senior management to secure strategic adoption and executive buy-in.
• Automation of Stubbing Processes with Generative AI: Designed a generative AI solution that automated build system processes, cutting manual deployment tasks by 60% and integrating seamlessly with Git workflows.
• Co-Simulation and RTE Standard Evaluation with Gen-AI: Accelerated compliance assessment for the RTE standard by 45% using generative AI tools and Python for evaluation.