CUDA Experts in Germany

• Deployment and scaling of existing ML initiatives, including demand and cash flow forecasts.
• Building robust monitoring with mlflow for data stability, model performance, and drift detection, as well as implementing additional ML use cases.
• Further development of an Agentic AI chatbot for transparent and easy-to-understand model explanations.

maturing their API Practices on both, a Business and Technology level. My role encompasses strategy, architecture, developer advocacy as well as hands on software engineering, enabling both technical teams and business leadership to adopt and act on API- centric principles effectively. Coincidentally, we also establish GitOps, DX and Platform Best practices with this project.

Highlights:

• Aligning executives with the initiative by clarifying strategy, replacing misconceptions and myths with facts, clarifying the value of existing assets and enabling informed decision-making
• Formulating a way forward for API Lifecycle Management at OTTO
• Driving platform progress and fostering developer engagement by hands-on engineering work towards strategic goals

API Lifecycle Management, Team Topologies, Organizational Evolution, Regulatory, Platform Advocate, Developer Platform, Communities of Practice, Terraform, Kotlin, Kafka, Kong, WSO2, Apigee, Gravitee, Backstage, AsyncAPI, OpenAPI, API Design, AWS, react, nodejs, typescript, redocly, reactive programming, CDC, golang, gingonic, GitOps, DX (developer experience), stakeholder management, roadmaps, workshops, discovery.

• 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.

• Developed a real-time video analytics proof-of-concept for deployment on NVIDIA Jetson edge devices.
• Implemented DeepStream pipelines including object detection, tracking, human pose estimation, face anonymization, and zone intrusion detection.
• Built a Qt/Python demonstration UI interfacing with the AI pipeline via REST APIs.

• 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).

• Developed an evaluation framework for AI-generated multiview driving videos intended for perception and embodied-AI/VLA-related training workflows.
• Designed automated checks for temporal coherence, cross-camera consistency, semantic correctness, and multiview geometric quality, exposing failure modes relevant to autonomous systems.
• Combined classical computer vision, learned visual representations, and vision-language models to convert complex video artifacts into measurable engineering signals.
• Built repeatable benchmarking and failure-analysis workflows to support model comparison, data-quality decisions, and system-improvement discussions.

• 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

• Engaged by MILLA Group (autonomous shuttle manufacturer) to integrate and harden a safety-critical AD stack toward production: audited the architecture across perception, HD mapping, and positioning, and delivered a gap analysis with remediation roadmap.
• Lead root-cause analysis of sensor failures across a deployed shuttle fleet; shipped remediation in a versioned AD release and drove vehicle-level field validation at multiple operational sites.
• Design and implement interfaces between perception, localization, and vehicle systems in C++; identify integration risks and drive resolution of cross-subsystem technical issues across the AD stack.
• Standardized the client's software development lifecycle by introducing Agile workflows and CI/CD pipelines, shortening integration and validation cycles.

• 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.

• Founded Latence to commercialise runtime safety patterns from HALO as a deployable product.
• Built end-to-end as single technical founder with open-source stack on NVIDIA ecosystem.
• Developed TRACE: real-time safety layer for knowledge agents and RAG pipelines with groundedness scoring, prompt-attack detection, GDPR redaction, context compression, audit-ready traces.
• Developed vLLM Factory: production inference framework on vLLM with custom Triton kernels and 12 parity-validated plugin models, achieving up to 11.7× throughput vs vanilla PyTorch.
• Developed ColSearch: single-node multi-vector late-interaction retrieval engine with Rust SIMD and fused CUDA, achieving 3.12× FastPlaid geomean QPS on BEIR-8 and a 1.58-bit quantized lane 6.4× smaller than FP16.
• Developed llm-opt: LLM compression research framework with hierarchical importance, structured pruning, tabu search, knowledge distillation.

• Further development and maintenance of data management software in the nuclear sector
• Processing and resolution of problem reports
• Bug fixing and defect remediation
• Performance optimization of legacy code
• Analysis and remediation of security vulnerabilities
• Specification and conceptual design of new features
• Modernization of legacy codebase to C++17
• Technologies & tools: C++, ClearCase, SQL, HTML, CSS, JavaScript, Git, Linux, Solaris, Shell-Script, VisualStudio
• Frontend – Smart Sensor Dashboard: development of a browser-based dashboard for real-time visualization of smart sensor data
• Technologies & tools: TypeScript, Angular, HTML, CSS, JavaScript, MQTT, VisualStudio
• Implementation of embedded safety software for a magnetic levitation elevator system
• Requirements engineering
• Documentation and implementation of safety software for the magnetic levitation elevator control system and the central management system
• Creation and execution of unit tests for all implemented modules
• Technologies & tools: C/C++, Jira, Bitbucket, Confluence, VectorCAST, MISRA-C, Lint, Doxygen, Git

• Automated driver assessment by programming temporal rule engines to evaluate lane-change execution safety, head-pose mirror checks, indicator usage cycles, and compliance with traffic lights and road signs
• Synchronized real-time traffic sign recognition and multi-state traffic light classification models with time-series CAN-bus telemetry and HD-map spatial priors to grade traffic rule adherence
• Trained and deployed distinct deep learning models optimized for interior cabin monitoring and exterior surrounding-area perception
• Combined perception outputs with camera intrinsics and horizon stability checks to execute 3D ground-plane object distance estimation assuming flat-ground geometry
• Deployed a split-compute edge network across a 10-vehicle fleet via VPN, implementing a zero-allocation host memory pipeline to eliminate frame accumulation latency (6×21 FPS per vehicle)

Technical audit for scientific software.

• Migration of the software development process of a medical technology software to C/C++ package manager Conan and development of macOS-specific system components