Data Science Intern

About the role

You will join the AI research team to support the development of Gotham, Deeptrack’s enterprise deep‑fake detection engine. Working closely with the Principal AI Researcher, you will contribute to model training, dataset curation, and performance evaluation.

Key responsibilities

• Run experiments on deep‑fake detection models using FaceForensics++ and real‑world data.
• Design and execute evaluation pipelines that measure precision, recall, and generalisation.
• Curate, clean, and augment datasets for model retraining and fine‑tuning.
• Research and prototype improvements such as temporal attention, multimodal signals, and adversarial robustness.
• Produce clear, reproducible research notes and model cards.

Required profile

• Currently pursuing or recently completed a degree in Computer Science, Data Science, AI/ML, or a related field.
• Intellectually rigorous – you question assumptions and document your reasoning.
• Bonus: experience with video/image forensics, GANs, diffusion models, or knowledge of C2PA/content provenance standards.

Required skills

• Strong Python programming skills.
• Familiarity with PyTorch or TensorFlow.
• Understanding of computer‑vision fundamentals and deep‑learning architectures (CNNs, ViTs).
• Experience with model evaluation metrics and statistical analysis.