Barae Rayed

Designed and implemented CI/CD pipelines using GitHub Actions for seamless zero-downtime deployments. Managed and scaled AWS infrastructure across 5 accounts, hosting 17+ EC2 instances with Auto Scaling Groups (ASG), supporting applications with over 6 million visits per month and reducing infrastructure costs by 15%.

Supported infrastructure for LLM deployment in a brain visualization platform. Developed InceptionV3-based model for simultaneous bone age and gender assessment from hand radiographs, achieving 95% accuracy in gender classification.

Engineered object tracking systems using YOLOv8 on RGB and thermal feeds. Integrated DeepSORT for real-time person tracking in surveillance applications. Optimized the deployment pipeline for ML models using CI/CD tools (e.g., GitHub Actions), reducing deployment time by 65% and improving reproducibility.

Built a U-Net model for hippocampus segmentation in MRI data, focusing on model architecture optimization. This work contributed to advancements in medical image analysis.

Currently pursuing a Master of Science degree with a focus on computational neuroscience and biomedical applications. Thesis research involves leveraging Large Language Models (LLMs) and 3D brain simulations for diagnostic support. Awarded a Full Academic Scholarship for academic excellence.

Grade: 3.70/4.00

Completed a Bachelor of Science degree in Computer & Biomedical Engineering. Graduated first in class with a GPA of 3.70/4.00, demonstrating strong academic performance in the field.