Image Processing Experts

Project: Defect Generation on Test-Bench Images of Metal Surfaces Environment: Automated Visual Inspection (AVI), Metallurgy & Manufacturing

• Objective & Implementation: Designed, architected, and trained Generative Adversarial Networks (Pix2PixHD / SPADE) for image-to-image transformation. Targeted generation of synthetic material defects (e.g., cracks, inclusions, scale) on rough metal surfaces under real test-bench lighting conditions for privacy-compliant and efficient dataset expansion (data augmentation).
• Technical Design: Implemented robust Generative AI and computer vision pipelines in Python and PyTorch. Used semantic segmentation approaches for mask-controlled defect synthesis and subsequent evaluation with EfficientDet object detection models.
• Business Impact: Massive dataset upscaling (10x) without time-consuming and costly physical test-bench runs, while significantly improving the detection performance of automated inspection systems.

Technologies & Skills Used: Python | PyTorch | SPADE | Pix2PixHD | EfficientDet | Machine Learning | Semantic Segmentation | Computer Vision

• Conclusion of partner agreements with OnePlan (portfolio management) and ForProject/EVMS (project controlling); ongoing qualification and implementation of both tools.
• Project management for the relaunch of [link] with a new focus on integrated PM/PPM toolchains.
• Development and implementation of approx. 60 PM standard methods (PMSP, CMSP, QMSP) according to ICB4 & PMBoK8 as a database application on MS Power Automate / M365 / MS Project, with a planned cloud launch in 2025.
• Deployment and cut-over standard process defined as Quality Gate QG07: go-live plan, cut-over plan, communication package, production launch, smoke test in production, hypercare team, incident and SLA management, confirmation of production stability and operational handover.
• Development of a classification and retrieval system (TOC) for ChatGPT projects to enable immediate cross-application object activation.

Tools: LinkedIn, Claude, ChatGPT, Gemini, Infinity, MS Copilot, OnePlan, EVMS/ForProject, Power Automate, SQL DB, O365, MS Project, MS Cloud, ICB4, PMBoK7, M365, Teams

• Development of scalable backend applications with C#/.NET and Java
• Design and implementation of distributed microservice architectures
• Development and integration of REST APIs for industrial applications
• Development of modern web applications with React, Angular, and TypeScript
• Implementation of MQTT-based communication solutions
• Integration of industrial protocols such as OPC UA and Modbus TCP
• Development of batch, process control, and HMI components
• Containerization and deployment of applications with Docker
• Conducting code reviews and supporting architecture decisions
• Close collaboration with product owners, QA, and interdisciplinary teams
• Analysis of business requirements and implementation of technical solutions
• Further development of existing software architectures with a focus on maintainability and performance

Technologies: C#, .NET, ASP.NET Core, Java, C++, React, Angular, TypeScript, Vue.JS, MQTT, OPC UA, Modbus TCP, Docker, GitLab, MariaDB, MySQL, Linux

• Role: Simulation Engineer
• Environment: Mechanical Engineering / Visual Inspection
• Goals & Implementation: Simulation of photometric-stereo setups to determine the best positions for cameras and light sources for each specific part.
• Business Value: Enabled a low-cost and scalable solution for determining part-specific hardware setups.
• Tech Stack: Python, Blender

• Portfolio development & customer acquisition
• Portfolio development (RAG, NLP fine-tuning, process automation with n8n) and active customer acquisition
• Positioning: GDPR-compliant, locally hosted AI solutions for SMEs

In this project, I was responsible for designing and implementing a new, modular, and highly scalable test bench platform for an automotive supplier. My focus was on developing a robust system architecture and programming the associated software, with UML modeling used consistently throughout. This structured approach significantly increased the reusability of individual LabVIEW test modules and sustainably reduced development time for subsequent projects. I also integrated modern automotive standards such as CAN FD, LIN, and safety requirements, making the solution future-proof.

Technologies: LabVIEW, Visio, UML, CAN FD, LIN, DMM, Safety, Image processing, Project management, HMI, C#, C++, Python, Rust, CI

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects

Independent engineering practice focused on custom AI systems, production delivery, and fractional technical leadership.

Selected client engagement: Scalutions

• Role: Serve as fractional CTO and hands-on technical lead, responsible for the architecture and agentic infrastructure behind its managed B2B outbound operation.

• Product: Designed and built OutboundLoop, an agentic SDR operating system for research, qualification, personalized outreach, campaign management, human approvals, measurement, and continuous improvement.

• Scope: Own the full system lifecycle—from business processes and agent behavior to context design, model routing, integrations, evaluation, telemetry, reliability, cost control, and production operations.

• Consulting and development of suitable communication concepts between S7-300 and S7-1500, taking the existing PROFIBUS infrastructure into account
• Technical support for connecting the S7-300 controllers to the existing recipe data block of the S7-1500
• Assisting in the development of the communication sequence for recipe access (read, write, acknowledge, status handling)
• Configuration of S7 communication (PUT/GET)
• Creation and adaptation of WinCC V7 scripts (C scripts and VBS scripts) for WinCC-based recipe management
• Development, optimization, and integration of recipe processes into the existing WinCC project structure
• Commissioning of the new communication interfaces and recommissioning of the recipe logic on existing systems
• Creation of technical documents: communication sequences, functional descriptions, commissioning documentation

Development of an iOS app for virtual try-on and outfit suggestions

The goal of the project is to develop a mobile application for personalized, photorealistic outfit suggestions. Users should be able to upload their own photos, try on clothes virtually, and find products that can be bought directly in the generated suggestions.

• Planning and implementation of the onboarding and photo upload in the iOS app
• Development of the mobile application with Expo and React Native
• Implementation of a Hono/Node.js backend for user, product, and generation processes
• Building an asynchronous processing pipeline with BullMQ and Redis
• Connection of PostgreSQL/pgvector and S3 for product, image, and generation data
• Integration of Gemini and OpenAI for outfit generation and image processing
• Implementation of a credit system and integration of RevenueCat
• Integration of Stripe Connect and affiliate product feeds for products that can be bought directly

Label: TypeScript, React Native, Expo, Hono, Node.js, PostgreSQL/pgvector, BullMQ, Redis, S3, Gemini, OpenAI, RevenueCat, Stripe Connect, Docker

• 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)

• Provided technical leadership for a 4-engineer team delivering 3 major client platforms in 12 months with microservices architecture and scalability solutions — 100% of scoped majors shipped ahead of schedule vs. planned milestones (baseline: prior releases often slipped 1–2 sprints).
• Ran AI model evaluation and model outputs evaluation on LLM/AI vendor APIs: safety, completeness, instruction adherence, and groundedness review before go-live; cut escaped bad outputs in AI-integrated release checklists from recurring UAT findings to near-zero on final promote.
• Drove API development and performance optimization for payment, exchange, and AI services; fail-closed error handling and payload validation reduced integration rework cycles by ~35% vs. the first AI integration pass.
• Applied software testing, testing frameworks, code quality assurance, and code refactoring with continuous integration gates; first-pass PR acceptance improved across the team and production hotfixes on AI adapters dropped noticeably after review standards landed.
• Owned DevOps practices: Docker, GitHub Actions, Jenkins-compatible pipelines, and version control workflows — cut deployment time ~50% vs. pre-automation baseline and stabilized releases across 3 client environments.
• Implemented verifier/oracle-style pass-fail checks in container sandboxes (Harbor/Terminal-Bench aligned); wrote technical documentation so failures cleared in one review cycle.
• Led cross-functional collaboration with product and client stakeholders; translated AI evaluation scores and risk findings into plain-language briefs for non-technical partners, unblocking go/no-go decisions without extra engineering meetings.
• Used agile methodologies for sprint planning and backlog ownership; mentored engineers so mid-level contributors owned AI adapter modules independently by mid-engagement.

• 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 and validation of control concepts for grid stabilization with MATLAB/Simulink.
• Modeling of converters (VISMA), grids, and loads to study frequency and phase behavior during load steps.
• Analysis of the influence of inertia, damping, and controller parameters on stability, power output, and ROCOF.
• Development of adaptive control strategies to improve synchronization and dynamic grid support.
• Creation of automated simulation and evaluation tools to assess different scenarios and parameters.