Hugging Face Transformers Experts in Germany

• 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.

• Founded an AI-powered scheduling and business-management SaaS for SMBs, owning technology strategy, architecture, product development, UX, billing and go-to-market execution.
• Architected and shipped a multi-tenant platform with REST APIs, RBAC, CRM, billing and notifications, powering the manager dashboard, admin console, booking experience and iOS/Android applications.
• Led and mentored 7 software engineers, 1 DevOps engineer, 1 QA engineer and 1 UX/UI designer, while remaining hands-on across backend, frontend and product delivery.
• Built AI voice and chat agents using Python/FastAPI, OpenAI and Anthropic APIs, RAG, pgvector and tool calling; integrated Twilio, Google Calendar/Meet, Stripe and Firebase.
• Owned production infrastructure and automated delivery across separate environments using Docker, Nginx, GitHub Actions and Grafana; represented the company at accelerators and international startup events.

Selected stack: Python, FastAPI, Node.js, Vue 3, React/Next.js, React Native, PostgreSQL, Redis, Docker

• Build and operate an end-to-end MLOps platform on Azure ML and Kubernetes (Kubeflow) for the automated deployment, monitoring, and scaling of forecasting models (including Temporal Fusion Transformer, Informer, Autoformer).
• Implement CI/CD pipelines in Azure DevOps for the full ML lifecycle – from resource provisioning (Terraform), data transformation (Hugging Face Datasets, Pandas, PyTorch, CUDA cluster) through training and evaluation to model registry and endpoint deployment.
• Integrate MLflow for experiment tracking, model versioning, performance monitoring, and automated registration in the Azure Model Registry.
• Develop and containerize PyTorch training jobs (Azure Notebook, Jupyter Notebooks) for price and time series forecasting (PFC models) with automatic rollout via Azure ML Endpoints and REST/gRPC interfaces, Docker containerization, secured with OAuth 2.0.
• Set up monitoring and alerting mechanisms (Prometheus, MLflow Metrics), log centralization, and cost monitoring.
• Automate infrastructure provisioning and model deployment using Terraform, Helm, and Azure CLI; connect to existing market data systems and event pipelines.
• Migrate existing workloads and databases (IONOS → Azure, MongoDB) with integration into central MLOps workflows and internal networks.
• Extend the platform with LLM-based tools (LangChain, LangServe) to integrate GPT-based analysis modules into existing Spring Boot services for market anomaly detection and automated reports.
• Analyze and architect a software solution to process large volumes of data efficiently (>3000 messages/sec.) (market data store).
• Spring Boot / Java 21 container development with RabbitMQ for distributing stock market data via MongoDB (Kubernetes) with fast storage of data in Redis RMaps, deduplication, forwarding messages to Read Model queues, and building Read Models for UI display in MongoDB.
• Integration of RESTHeart to create a REST API for MongoDB.
• Build an Angular frontend to simplify data queries and master data maintenance.
• Agentic coding with remote and local LLMs (Claude Sonnet, Ollama Qwen) and MCP servers.
• Develop Python scripts for transforming and cleaning incoming stock market data (Pandas, scikit-learn).

• Spearheaded the integration of a custom Transformer-based encoder into the AFFGANwriting pipeline, replacing the legacy VGG19 architecture to capture richer, high-fidelity writer-style representations.
• 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.
• Enhanced OCR performance by 20% by implementing a teacher-student framework that leveraged a TrOCR benchmark model for auxiliary training alignment

Development of a route planner for incident communication.

• Development of the REST API
• Set up a patch system for maintaining the routing graph
• Expansion of the testing infrastructure
• Performance and memory optimization (JMeter, JFR)

Technologies: Java 21, Spring Boot, JGraphT, Flyway, MapStruct, Caffeine, ShedLock, JMeter, Kubernetes, JFR

• Developed and implemented AI-based perception and multimodal systems for real-world environments
• Built, trained, and evaluated Machine Learning and Deep Learning models using Python, PyTorch, TensorFlow, and OpenCV
• Worked with Vision-Language Models (VLMs), Large Language Models (LLMs), transformer-based architectures, and multimodal AI systems
• Applied LoRA-based fine-tuning techniques and experimented with diffusion models for generative and multimodal AI applications
• Developed multimodal perception pipelines using camera, LiDAR, and sensor data
• Designed end-to-end workflows for data processing, model training, evaluation, benchmarking, and robustness analysis
• Utilized HuggingFace Transformers and modern Deep Learning frameworks for AI experimentation and deployment workflows
• Applied GPU-accelerated computing, CUDA-based processing, ONNX, and TensorRT optimization for efficient inference and large-scale model training
• Collaborated with industry partners including Valeo and REHAU on applied AI and intelligent system projects
• Developed scalable AI architectures and prototype software solutions for automation and perception tasks

• Developed end-to-end reproducible ML pipelines (PyTorch) with data versioning (DVC), experiment tracking (MLflow), automated testing (PyTest), and CI/CD across all training workflows.
• Scaled Vision Transformer and CNN training across NVIDIA A100 GPU clusters (CUDA, DDP, SLURM); applied hyperparameter optimization (W&B Sweeps) to reduce training overhead and identify optimal configurations.
• Developed a real-time 3D human motion generation system (ViT, VQ-VAE, SMPL-X/PIXIE) for personality-conditioned avatar synthesis; achieved state-of-the-art FID = 6.15 and P-FID = 10.31 on the UDIVA benchmark.
• Validated model expressiveness through structured user studies, achieving 86% accuracy in distinguishing extroverted vs. introverted avatar behaviors.
• Optimized inference pipelines by deploying PyTorch models via TensorRT and ONNX Runtime into native C++ code; benchmarked performance.

• Introduced an integrated approach for structural damage detection across concrete, steel, and glass using advanced technologies such as LiDAR and thermal imaging. Highlighted cross-material interactions to enhance diagnostics and enable predictive maintenance.

• Developed an NLP-based medical note simplifier that transforms complex clinical instructions into plain, child-level English. Applied prompt engineering with Flan-T5 transformer models to extract patient-relevant actions and rephrase them into clear to-do items. Built dual Flask and Tornado backends with a printable web interface.

AI-driven automation of purchasing on a printing company's website, including selecting delivery times, order options, ordering, payment, and uploading print data from the Lumiz Cloud.

• Reviewing functional and technical requirements from a testing perspective
• Creating test cases and automated tests to validate requirements
• Performing manual and automated functional, end-to-end, and regression tests
• Documenting test results and tracking defects
• Using models like GPT-4, BERT, and Hugging Face Transformers for automated test case generation, analysis of test results, and improving test coverage, including bias checks and security reviews
• Techs: MS Office, Jira, Zephyr, Confluence, Tosca, stakeholder communication, Agile, Kanban, Scrum, OpenAI API, Hugging Face, PyTorch, LangChain.

• Integrated LangChain middleware between AEM and SAP PIM system
• Developed a FastAPI interface for system communication
• Implemented vector embeddings for semantic product search
• Evaluated LLM models (Vertex AI/Gemini, LM Studio, Hugging Face, OpenAI) for product analysis
• Developed an AEM component to display product recommendations and integrated the recommendation API into the AEM authoring process
• Designed and implemented Pinecone vector database for product embeddings
• Optimized response times and caching strategies
• Evaluated Vertex AI Studio for LLM testing and prompt workflows
• Implemented secure API routing and access control for AI components via FastAPI and gateway validation

• Design, preparation and delivery of a webinar on 'RAG in Practice: How publishers create real value with AI'
• Preparing technical and strategic content on Retrieval Augmented Generation (RAG) for a mixed audience from the publishing industry
• Presenting specific use cases, technical backgrounds, common challenges and solution approaches when using RAG
• Providing practical insights into data preparation, model selection and output optimization in the context of digital publishing portals
• Conceptual and technical preparation of the webinar
• Selecting and presenting practical use cases from the publishing environment
• Developing technical backgrounds for implementing RAG systems
• Presenting and explaining typical challenges and solution strategies
• Large Language Models (LLMs)
• Retrieval Augmented Generation (RAG)

• Performed security assessments and penetration testing on Microsoft AI models for text, image, and video generation.
• Conducted prompt injection attacks through diverse input vectors, including crafted text, steganographic images, and manipulated visual elements (e.g., varying opacity and embedded content).

• Applied advanced machine learning techniques by developing a multi-strategy prompting framework (zero-shot, few-shot, CoT, instruction tuning) to extract structured data from complex financial and medical datasets, significantly enhancing model reliability and achieving an 18% improvement in F1-score through rigorous evaluation using advanced metrics (ROUGE-L, METEOR, Cosine Similarity).
• Designed scalable structured-output workflows and built automated monitoring pipelines (spaCy, ClearML) for continuous performance tracking, simulating real-world MLOps principles.
• Refined prompt strategies iteratively based on meticulous error analysis to ensure robust, production-ready performance.