Computer Vision
- OpenCV
- YOLOv8
- CNNs
- Tracking
- OCR
- MediaPipe
Computer Vision / AI Engineer
Rassem Bali
I build practical vision systems.
Computer Vision Engineer focused on deep learning and production-ready AI systems that solve real operational problems.
About
Computer vision engineered for real-world impact.
I work as a Computer Vision Engineer building end-to-end AI solutions across retail analytics, medical imaging, and intelligent automation. My focus is clear: robust model performance, clean deployment paths, and practical business value.
My projects include in-store queue analysis, bird's-eye view heatmap analytics, 3D brain tumor segmentation, OCR systems, and depth estimation pipelines. I also trained 40+ students through hands-on workshops covering OpenCV, YOLOv8, and deep learning workflows.
I am open to remote roles, research collaborations, and freelance projects where technical quality, fast execution, and clear communication are essential.
Skills
Core stack for vision engineering.
Deep Learning
- PyTorch
- TensorFlow
- ONNX
- Evaluation
- Training pipelines
Deployment
- FastAPI
- Docker
- Inference optimization
- Streamlit
Tools
- Git
- Linux
- GPU workflows
- Python
Experience
Applied AI and computer vision experience.
Computer Vision Engineer
VisShop AI
Worked at VisShop AI, a startup specializing in artificial intelligence and computer vision solutions for the retail sector. Contributed to the design and development of advanced computer vision systems with strong technological and operational impact. Developed an intelligent in-store queue analysis system to optimize customer flow, implemented age and gender estimation models from video streams, and designed heatmap-based analytics to analyze customer behavior and attraction zones within retail environments. The two featured retail projects in this portfolio, In-Store Queue Analysis System and Bird's-Eye View Heatmap Analytics, were completed under VisShop AI. This role required strong technical rigor, adaptability, and innovation, and strengthened expertise in applied AI and real-world computer vision deployments.
Skills: OpenCV, Python, and 10+ additional skills
DevOps Intern
KPIT
Applied Docker and Kubernetes for scalable workflows and researched AI-driven CI/CD pipelines.
Skills: Docker, Kubernetes, and 2+ additional skills
Robotics Intern
IMSR TUNISIA
Worked on robotics systems using ROS2 and reinforcement learning techniques.
Skills: ROS2, Reinforcement Learning, and 3+ additional skills
Data Science Intern
Digital Research Center of Sfax
Worked on data science and deep learning tasks with a focus on artificial intelligence applications.
Skills: Deep Learning, Artificial Intelligence (AI), and 2+ additional skills
Projects
Selected projects with demo videos.
Computer Vision / Retail Analytics
In-Store Queue Analysis System
An intelligent queue detection and analysis system for estimating queue length, waiting time, and customer flow.
Computer Vision / Retail Behavior Analysis
Bird's-Eye View Heatmap Analytics
A heatmap analytics system for understanding customer movement, attraction zones, and retail space utilization.
Medical Imaging / Deep Learning
3D Brain Tumor Segmentation (U-Net)
A 3D U-Net project for brain tumor segmentation from MRI scans with volumetric medical data.
Source code
Contact
Let's work together.
For research opportunities, remote positions, or freelance collaborations, contact me directly.