Celery Experts in Germany

• Created complex backend systems (Fastapi Python, GCP cloud functions, APIs, integration tests) using Typescript.
• Worked with firebase and firestore databases, implementing transactional operations, scheduling jobs, and migrations.
• Implemented GCP dashboards for thorough monitoring and custom alerts in case of anomaly traffic.
• Implemented Sentry for better debugging, error tracking and overall monitoring of the Next.js frontend.
• Implemented story tests for UI related testing.
• Implemented Typesense in Python Fastapi backend, for improved text based searching along with typo handlings.

Manufacturing intelligence platform with enterprise workflows, RAG, real-time AI assistant features, and multi-repository backend architecture.

• Built and extended production AI/backend services with Django, DRF, FastAPI, GraphQL, Celery, PostgreSQL, MySQL, Redis, and WebSockets across a modular multi-repository platform.
• Contributed to ARIS V2, a real-time manufacturing AI assistant using LangChain, LangGraph, MCP tool orchestration, planning/execution flows, OpenAI, AWS Bedrock, Qdrant, and Elasticsearch/OpenSearch-backed retrieval.
• Supported rollout expansion from ARIS V1 in 4 of 17 client production plants to ARIS V2 currently active in 13 of 17 plants, increasing real-world deployment coverage to more than 50% of the client footprint.
• Worked on document-grounded RAG functionality including ingestion, OCR, chunking, embeddings, indexing, retrieval, reranking, and grounded answer generation for industrial workflows.

Stack: Python, Django, DRF, FastAPI, LangChain, LangGraph, GraphQL, Celery, WebSockets, OpenAI, AWS Bedrock, Qdrant, Elasticsearch/OpenSearch, PostgreSQL, MySQL, Redis, Docker.

• Expert-supervised AI systems for scientific reasoning, model evaluation, and research workflows.
• Built the IAS Problem Solver, an orchestrated system for difficult mathematical reasoning; it achieved 84% in one submitted answer set on the Leipzig mathematics benchmark.
• Built a resumable state-machine pipeline for research-grade mathematics benchmark generation: source selection, LLM-agent-based phenomenon discovery, task synthesis, gold-answer and certificate generation and validation, probing, repair, human feedback, and quality gates, targeting tasks that are difficult, natural, verifiable, and cost-effective.
• Current work extends this into budget-aware AI research workflows for real scientific problems with expert review.

Tech stack: Python, OpenAI/OpenRouter-compatible APIs, embeddings, RAG, SQLite.

• ▶ 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.

• Developed backend for Audit Management Tool using Node.js/Express with Workday API integration.
• Built secure file handling (PDF, PPT, CSV) with AWS S3 and database support via PostgreSQL, Prisma, and MongoDB.
• Implemented validation, role-based access, and audit trails for compliance and data integrity.

• 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.

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.

• Engineered production-ready Azure environments using Terraform, ensuring consistent infrastructure parity across VNets and Resource Groups
• Implemented Microsoft Fabric tenant and workspace architecture for multi-stage Medallion data processing pipelines
• Designed secure data pathways using Managed Private Endpoints for isolated Azure Storage access
• Managed Service Principals and authentication tokens for secure REST API integrations

• Expansion and maintenance of existing custom information systems based on Django
• Technologies used: Django, Django REST Framework, MySQL, Docker

• Implemented and maintained logistics-domain applications using Angular, C#, ASP.NET, HTML5, CSS3, JavaScript, AJAX and Bootstrap
• Analyzed, designed, coded and deployed backend services and integrations using .NET, XML Web Services and RESTful APIs
• Developed automated SSIS packages and scheduled ETL jobs to support data workflows
• Built and maintained Python scripts for automation and prototyping; applied Cursor AI to build/refactor full-stack AI/ML model integrations
• Implemented unit and integration testing (NUnit) and conducted performance tuning for backend services
• Managed source control and CI/CD using GitHub, Azure CI/CD pipelines and TeamCity

• Built multi-tenant warehouse management SaaS: 40 API modules, 150+ routes, real-time updates via SignalR
• Technologies: React, TypeScript, Redux Toolkit, RTK Query, Webpack, .NET 8, PostgreSQL, SignalR, Docker, GitHub Actions
• Landing: Next.js 14, Tailwind CSS, 17 localizations, Stripe payments (SEPA + cards)
• Testing: xUnit (150+ files), Jest, Playwright E2E; CI/CD: Docker, GitHub Actions
• Telegram AI agent: daily inventory reports, shipment alerts and warehouse monitoring delivered to mobile
• Background jobs and scheduled tasks for automated reporting, alerts, and data synchronization
• Built German e-invoicing SaaS (XRechnung, ZUGFeRD), GDPR compliant, multi-tenant architecture
• Technologies: React, TypeScript, RTK Query, Python, FastAPI, PostgreSQL, Redis, Celery; Testing: pytest (294 tests), Playwright
• Implemented async task queues (Celery + Redis) and scheduled jobs for invoice processing, email notifications, and DATEV export
• Developed AI-powered content automation platform: analyzes Git commits, generates and publishes posts to LinkedIn and Discord, responds to GitHub Issues automatically
• Cron-based automated publishing pipeline and scheduled content generation and distribution across platforms
• Multi-LLM architecture (OpenAI, Claude, Gemini) with pluggable provider system and RAG-based knowledge assistant integrated across all SaaS products

• Project management
• Building an internal IAM team
• Okta
• Project management
• IAM processes

• Developed a multi-agent system connecting LangChain ZeroShotAgent with custom tools for live APIs and task automation.
• Built a FastAPI backend for Jira ticket creation, triage and assignment, auto classification of severity, deduplication, SLA setup, on-call rotation, bidirectional sync of status and comments.
• Added Slack alerts and RAG knowledge lookup with FAISS or pgvector to suggest fixes, optional PagerDuty escalation on policy breaches.
• Orchestrated agents with a router and a Celery plus Redis queue, retries with backoff, rate limits, idempotency keys, human in the loop approvals.
• Implemented guardrails and observability, prompt versioning, token and cost budgets, PII redaction, tool-use allowlists, timeouts, OpenTelemetry tracing, dashboards for accuracy and latency, deployed on Kubernetes with feature flags and canary rollouts.