Temporal Experts in Germany

• Engineered and validated a full-vehicle thermal management system in MiL simulation, achieving 95% correlation accuracy against real-world vehicle measurements, directly supporting virtual calibration and reducing dependency on physical test benches.
• Led end-to-end Model-in-the-Loop (MiL) simulation development using AVL CruiseM and MATLAB/Simulink, covering system architecture, parameterization, and validation.
• Acquired and analyzed vehicle sensor measurements (temperature, volumetric flow rate) using dSpace MicroAutoBox (HiL) and IPEmotion, translating raw data into actionable calibration insights.
• Calibrated and optimized critical actuators and thermal components - pumps, valves, electric heaters, heat exchangers, and refrigerant circuits and identified/integrated previously missing physical behaviors to close the gap between simulated and real vehicle performance.
• Designed and tuned an integrated actuator controller with precisely calibrated parameters, producing a high-accuracy virtual model adopted for downstream development use.

• 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.

Zerobits is my vehicle for AI-powered automation and custom software development with a clear principle: AI solutions that reach production, not pilot stage. I design and build the systems myself - from first concept and architecture through implementation to deployment and operations.

My focus is on replacing repetitive, manual work with reliable automation and connecting disconnected tools and data sources into one dependable overall system.

Selected work:

• Design and implementation of LLM-based agent systems and RAG pipelines (Anthropic Claude, Mistral, MongoDB Atlas Vector Search + RAG)
• Workflow orchestration for long-running, fault-tolerant business processes using Temporal (temporal.io): saga patterns, event-driven architecture, retry and compensation logic, connecting third-party APIs and internal services into automated end-to-end processes
• Full stack product development: SaaS architecture on Kubernetes, TypeScript/React/NestJS, admin tooling with refine.dev and MUI
• AI-assisted development workflow as standard practice to deliver production software at a fraction of traditional timelines
• Full stack product development: multi-tenant SaaS architecture running on Kubernetes, backend with NestJS/Node.js and Python, frontend with TypeScript, React and Next.js, admin tooling with refine.dev and MUI, CI/CD with GitHub Actions

One of these projects is a product I own and operate - free of any NDA restrictions. I'm happy to demonstrate it end to end.

• Topic: Object Detection and Semantic Segmentation for (AUV) Systems using Transformer-Based Vision Models and Sensor Fusion.
• Designed and implemented an end-to-end multi-sensor fusion perception pipeline (Camera, LiDAR, IMU) in ROS
• Developed CNN-based Machine Learning model (YOLOv8) and Transformer-based vision models for real-time object detection
• Processed and clustered 3D LiDAR point clouds using DBSCAN, RANSAC, and voxel grid filtering to enable robust object localisation in noisy environments.
• Designed Bayesian Network models (GeNle) for probabilistic reasoning and sensor-level decision fusion under uncertainty.
• Applied Kalman filtering for sensor state estimation, temporal alignment, and smooth object tracking, reducing false positives in safety-critical scenarios.
• Evaluated system performance under realistic driving dynamics, improving tracking stability and overall perception robustness.
• Built deep learning pipelines for training, validation, and performance evaluation of perception models using sensor data.

• Built and verified Zynq-7000 (Zybo Z7-10) FPGA prototypes in Xilinx Vivado – AXI IP integration, bitstream generation, hardware bring-up, timing-closure checks and waveform-based debug to confirm expected RTL behaviour.
• Set up Cadence Virtuoso schematic/simulation flows and documented settings, results and methodology for reproducible experiments – supporting structured verification and research documentation.
• Wrote Python automation for log parsing, structured data reporting and result analysis; worked daily in version-controlled Linux/Git workflows.

• 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)

• Developed and implemented organization-wide discovery framework based on Ulwick’s Outcome-Driven Innovation; enabled 7 Product Owners to systematically identify and quantify unrealized value through shared outcome language and opportunity scoring methodology
• Transformed Product Owner role from backlog clerks to strategic experimenters; established dedicated time budget for autonomous hypothesis testing and discovery activities
• Rebuilt customer journey maps to start at actual user need (tool selection phase) instead of platform entry point; eliminated manual data aggregation work previously done by project teams
• Implemented OKR framework across 4 product teams; defined quarterly objectives with measurable key results (e.g., 40% reduction in manual integration effort, self-service adoption increase)
• Unified 3 separate platform roadmaps through cross-team dependency mapping and shared service agreements
• Supported enterprise sales cycle with ROI modeling and technical due diligence for automotive and defense customers

• Developing a multi-class classification model to predict plant composition and its spatial and temporal changes using predictors, including satellite images, climate time series, and other environmental data such as land cover, human footprint, bioclimatic, and soil variables.
• Developing recommender systems using contextual bandits for an e-commerce platform.
• Building deep neural network models that predict flood-affected areas.

• Implementation of a Network Access Control (NAC) security system at 106 locations in the USA, Mexico, and three European countries to safeguard facilities against cyberattacks.
• Management of infrastructure renewal in the core network in the USA and Mexico, transitioning to a new hardware provider.
• Optimization of LAN, WAN, and WLAN infrastructure, including division of network topology into dedicated VLAN segments for IT and OT separation.
• Development of project scope definition considering technical and organizational business requirements.
• Integration of local IT resources and external suppliers to capture functional, temporal, and financial requirements.
• Specification of work packages for US/EU NAC system implementation and modernization of the US core network.
• Acquisition of necessary approvals for project execution and budgeting from the board.
• Creation of rollout plans, inventory data collection, data validation, and drafting detailed project definitions.
• Development of a central project control application.
• Execution of pilot implementations to test developed solutions.

• Release / further development of SAP Commerce (2105), Azure DevOps, IntelliJ IDEA
• Design and development of new features
• Performance optimization of Hybris (SAP Commerce 2105)
• Customizations
• Maintenance and support
• Integration tests and quality assurance
• Code optimization
• Documentation

• Analysed German transmission networks with > 70 % renewable penetration, running N-1 contingency studies to quantify grid resilience.
• Develop sector coupling energy models for Germany 2030-2050 with high spatial and temporal resolution.
• Quantified technical & economic benefits of flexibility levers such as Dynamic Line Rating (DLR) or Demand Side Management (DSM).
• Co-develop and maintain eTraGo, an open-source Python tool for techno-economic network optimisation and spatial/temporal clustering.

• Building the company with a focus on connectivity for IIoT and Industry 4.0, iRPA/process automation, advanced robotics and smart systems, sensors and services
• Project management and software architecture for IoT gateway development (since 2020) with protocol translation, IT/OT convergence and GRC
• Developing RPA bots for automating and monitoring industrial processes with an agent-based AI approach (since 2020)
• Implementing unsupervised clustering and anomaly detection for time series data in big data streaming pipelines (since 2021)
• Introducing a Docker-based release train for OTA updates with DevSecOps and CI/CD (since 2018)

• Responsible for software engineering and DevOps in the Data & AI Platform - Intake and PubSub projects at STACKIT, the cloud provider of the Schwarz Group.
• Technologies: Golang, Kubernetes, Kubernetes operators, OpenAPI v3, REST API, Azure DevOps, CI/CD, k6, Kafka, Strimzi, Apache Iceberg, RBAC, IAM, Terraform, Helm, Infrastructure automation, Load balancing, Traefik, ArgoCD, kuttl, Kyverno chainsaw, Kustomize, Velero, Prometheus, Grafana, Checkly / Playwright (TypeScript), NATS/Jetstream, WebSockets, gRPC, SSE