AI software engineer · Malaysia

Yogeswary Mohan

I build AI tools that detect deepfakes, help review code, and turn images into accessible descriptions.

Yogeswary Mohan

Selected work.

ANIMATED WALKTHROUGH01 / 03
VISTA / VIDEO ANALYSISSIMULATED
SAMPLE VIDEO
ILLUSTRATIVE FRAME
DETECTION PIPELINE
Extract visual features
Compare across frames
Highlight regions
Regions marked for review

COMPUTER VISION · FINAL-YEAR PROJECT

Vista

A video deepfake detector that combines visual and temporal analysis with attention to highlight potentially manipulated facial regions.

  • CNN
  • LSTM
  • Graph attention
How I built it

I used a CNN to extract visual features and an LSTM to detect patterns over time. A graph attention network highlights facial regions that contributed to the prediction.

Experience.

  1. Mar–Aug 2026

    Garmin Malaysia

    New-Tech Research Engineer Intern

    Automated API documentation and worked on camera calibration and storage dispatch for robotic automation.

  2. Oct 2024–Jan 2025

    Sana’a University

    Freelance Software Developer

    Built an Android AR app with ARCore, working on real-time 3D rendering and surface detection.

  3. 2022–2026

    Universiti Putra Malaysia

    Bachelor of Computer Science

    Built Vista, my final-year project on detecting deepfakes in video.