YOLO Experts in Germany

• Led strategic software development of fusion algorithms for precise object tracking, trajectory prediction, and environment modeling based on multimodal sensor data (e.g., camera, LiDAR, radar, GNSS, IMU)
• Developed and implemented navigation algorithms for autonomous vehicles, including path planning, obstacle avoidance, and sensor fusion of visual, inertial, and distance-based sensor sources
• Automated extraction and training processes with CI/CD
• Developed and optimized data pipelines and processes in Microsoft Azure using Apache Spark, Databricks, and PySpark
• Developed and optimized embedded software for automotive control units
• Designed latency-critical software for real-time control in robotic systems with RTOS (freeRTOS, SAFERTOS)
• Used the Vector toolchain (CANdela, DaVinci, CANoe) for configuration and diagnostics
• Optimized existing data pipelines and processes (ETL, data warehouse, SQL)
• Developed and trained machine learning models using PyTorch
• Created deep-learning-based object detection and visual SLAM algorithms, trained on combined data from camera, LiDAR, and IMU sensors
• Implemented computer vision algorithms for object detection and classification in robotic systems using OpenCV and YOLO, utilizing synchronized image and depth data
• Implemented behavior-based control systems for autonomous robots using ROS2 Behavior Trees
• Performed testing, release, and integration of sensor fusion algorithms into automotive production programs
• Ensured adherence to proper software development processes and safety standards to guarantee high data quality (MISRA, ISO 26262, ASPICE)

• Created a multi-agentic system supported by a knowledge graph to automate drafting of research papers
• Used multiple experts (OpenAI models) collaborating during document drafting
• Extracted useful information from the knowledge graph
• Technologies: LangChain, LangGraph, Smolagents, LlamaIndex, dspy
• Infrastructure: Terraform and GitHub Actions (CI/CD) on AWS
• Deployed initial application as a Streamlit app

Re-platforming an e-commerce shop to a microservice architecture

• Goal: Replace an outdated Shopware system with a scalable, future-proof solution based on microservices and a headless architecture.
• Led a full architecture consulting process and defined the microservice boundaries based on a headless architecture with commercetools as PIM/OMS and Next.js as the frontend solution.
• Developed and integrated several decentralized services (e.g. internationalization, personalization).
• Took over the configuration of central third-party systems such as Contentstack and Algolia.
• Built a stable cloud infrastructure on Google Cloud with monitoring via Grafana.

Technologies: commercetools, Next.js, Contentstack, Algolia, Google Cloud, Grafana, TypeScript, Shopware

Development of an international e-commerce platform

• Goal: Build a high-performance, user-friendly and international e-commerce platform.
• Defined a scalable, high-performance and maintainable software architecture that served as the foundation for the platform's international expansion.
• Selected a best-of-breed technology stack that enabled the development of an industry-leading shop and reduced development effort for new features by 30%.
• Ensured seamless integration of critical third-party systems (PIM, CRM, ERP) to guarantee end-to-end business processes and a consistent data foundation.
• Implemented comprehensive tracking and analytics tools for continuous performance monitoring and optimization of the customer journey.

Technologies: React.js, Next.js, commerceTools, Algolia, Salesforce, Heroku, CI/CD, PHP, Google Analytics

AI-powered personalization and customer data platform in e-commerce

• Goal: Replace static content with a dynamic, AI-based personalization strategy to increase user relevance and automate marketing processes.
• Designed and built a customer data platform to aggregate and combine customer and analytics data from distributed sources.
• Implemented automated categorization of customer profiles as the basis for delivering personalized content and product recommendations in the Shopware frontend.
• Developed a semantic similarity algorithm based on Python and OpenAI to calculate product and content similarity from user profiles.
• Built the technical connection to retail media platforms to control external ad placements along the customer journey.

Technologies: Shopware 6, Python 3, OpenAI, Elasticsearch, PHP, Symfony, Twig

Shopware tracking & consent architecture (GDPR) for 4 online shops

• Goal: Build a unified, GDPR-compliant tracking infrastructure across multiple shops with central consent management across several Shopware instances.
• Defined a comprehensive tracking guide and developed a modular architecture compatible across multiple Shopware versions.
• GDPR-compliant integration of Usercentrics and Adobe Launch through a central tag manager.
• Full tracking setup (page, order, product, user) incl. partner-specific tracking (Emarsys, Channelpilot, etc.).
• Detailed event and error tracking to proactively identify technical drop-offs.

Technologies: Shopware, Adobe Analytics, Usercentrics, Tag Manager, PHP, MySQL, GDPR

AI/LLM search engine with RAG and hybrid search (Python, Elasticsearch)

• Goal: Build an AI-powered search engine with RAG architecture and hybrid search to accurately match service providers from over 500,000 company records.
• Developed an automated data pipeline (web scraping + LLM) that continuously crawls company data and converts it into structured formats using LLMs.
• Implemented a RAG workflow incl. vectorization for semantic search to increase search accuracy and relevance.
• Configured and fine-tuned Elasticsearch for hybrid search (vector + keyword search).
• End-to-end development of backend API, frontend and deployment on live servers.

Technologies: Python, FastAPI, Elasticsearch, LLM, RAG, React, Docker, Web Scraping

AI/computer vision system (Python, ML) – object detection under difficult conditions

• Goal: Develop an AI-powered recognition system with reliable performance even in rain, fog, snow and darkness.
• Built and annotated a large training dataset incl. difficult conditions.
• Trained a YOLO-based object detection model; carried out systematic error analysis and improved data quality and preprocessing.
• Coordinated with stakeholders through regular status updates.

Technologies: Python, Machine Learning, TensorFlow, PyTorch, YOLO, OpenCV

• Leading AI development for aquaculture startup, optimising shellfish visual assessments with machine learning and computer vision.
• Development and systematic evaluation of ML/CV algorithms for shellfish condition and morphometrics, using Python, Pytorch and MLFlow.
• Analysis of model performance, including identification of failure modes and edge cases in production deployments.
• Design of annotation strategies and refinement of labelled datasets for computer vision tasks.
• Detailed analysis of system performance and communication of findings through publication-quality technical reports to investors and fellow R&D staff.
• Responsible for delivery of technical roadmap.

• 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.

• 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)

• Built a Trend-Scouting AI system to automate technology intelligence in power electronics and semiconductors, combining Azure OpenAI with LangChain, Scrapy-based web crawling for structured, noise-free data acquisition, and automated PDF reporting for internal R&D use. Developed a FastAPI-based (Uvicorn) web application to validate LLM outputs, test prompt strategies, and enable interactive system evaluation.
• Developed a real-time STM32 binary telemetry debugger with a PyQt-based GUI, featuring header-based frame synchronization, anomaly detection, template-driven payload decoding, time-aligned buffering, and live signal visualization.
• Developed an AI-driven power inductor designer using surrogate regression models for accurate electromagnetic and thermal prediction. Integrated multi-objective NSGA-II optimization to generate efficient, manufacturable designs.

• Developing methods for monocular 3D facial reconstruction and personalized geometric modelling from mobile imagery
• Building learning-based approaches for facial shape estimation, video-based facial analysis, and privacy-preserving visual learning

• Developed a deep learning system with multi-view Basler cameras for markerless 3D pose estimation

• Showcasing the world's first fully immersive AR glasses experience in a moving car at CES 2024.
• Speaker about augmented reality at international conferences (e.g. the AR Ride Concept @ Unite 2024).
• Lead a 12-person interdisciplinary software team developing Android head-unit integrations, navigation & ADAS UI, and embedded software.
• Define technical direction, drive cross-domain architecture and integration, and mentor engineers across Android, UI/UX and embedded stacks.
• Oversee a small fleet of test vehicles for validation, tests, and data collection.

• 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.

• Developed ASR and TSR-based speech processing pipelines on AWS, enabling efficient feature extraction and scalable deployment for speech and text analytics.
• Built a Multimodal Speech Emotion Recognition system combining NLP and deep learning (audio + text), achieving 98% accuracy and supporting real-time, cloud-based inference.
• Designed and optimized end-to-end model training and evaluation workflows using AWS services (S3, EC2, Lambda) to ensure performance, reliability, and reproducibility.
• Created and deployed interactive, user-friendly dashboards for data visualization and insight generation, supporting research teams and management in data-driven decision-making.

• Evaluation and analysis of camera-based traffic light and sign recognition system on various LLM-based autonomous driving systems (LMDrive, BEVDriver)
• Implemented VLM based traffic notice instruction generation unit for closed-loop autonomous driving system which alerts driver in unforeseen driving incidents
• Developed independent LLM-based local chatbot with Llama, DeepSeek and Qwen including MLflow evaluation framework

• Developed an end-to-end AI pipeline for analyzing 2D exploded-view drawings using computer vision and deep learning models.
• Integrated YOLO-based object detection (Bounding Boxes, Post-Processing, Overlap Handling) for accurate part and callout detection.
• Applied the Segment Anything Model (SAM) for fine-grained segmentation and separation of individual components.
• Implemented OCR and feature extraction modules, and compared Vision Language Models (VLM) and traditional computer vision approaches in terms of accuracy, runtime, and scalability.