Professional Overview
Computer Vision Engineer specializing in 3D reconstruction & HPC deployment. At Lund Uni, I built multi-sensor 3D tracking pipelines & optimized YOLOv11/ViTPose models (>85% mAP, 25% less latency). Cut data prep by 80% via Blender/Python synthetic pipelines. MSc Data Science. Seeking applied AI roles in robotics & autonomous systems.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Engineered 30-keypoint custom dataset (1,200+ frames) for pose estimation.
- Trained ViTPose, HRNet, ResNet & YOLOv11 models on HPC computing clusters.
- Built end-to-end CV pipelines for occlusion and distal landmark tracking.
- Evaluated accuracy-latency tradeoffs for real-time and offline deployment.
Key Achievements / KPIs
- Awarded 3 Erasmus grants for academic excellence and international research.
- Master's thesis on deep learning benchmarking currently pending publication.
- Balanced 83 FPS inference with sub-pixel accuracy via Pareto optimization.
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Benchmarked YOLOv11, ViTPose & ResNet for markerless pose estimation.
- Built semi-auto data labeling pipelines using OpenCV and CVAT.
- Led a 3-person team through model benchmarking and codebase reviews.
- Optimized neural networks via structural pruning on HPC clusters.
Key Achievements / KPIs
- Reduced inference latency by 25% while keeping accuracy above 95%.
- Slashed data preparation and annotation timelines by 80%.
- Achieved >85% mAP on custom datasets using edge-ready DL models.
Education
Field of Study: Machine learning and computer vision
Areas of Expertise
AI & Machine Learning Engineers
Design, train, and ship production ML models — from data pipelines to model inference at scale. Covers supervised learning, neural networks, LLM integration, and model optimisation.
