Job Description

IN-CYPHER is hiring an AI Research Intern to work across Themes 3 and 4. You will explore new approaches to synthetic data generation under differential privacy, aiming to push the utility–privacy frontier for text and multimodal data. A key part of the role is building and validating privacy auditing tools, such as membership inference attacks tailored to synthetic datasets, and designing evaluation protocols to quantify privacy risk.

Requirements:

Education: Currently enrolled in or have completed an undergraduate or graduate program in Computer Science/Engineering or a closely related ML/AI field.

Background: Experience in software development, including:

Proficient coding skills (e.g., Python)

Deep learning frameworks (e.g., PyTorch)

Experience with LLMs/NLP and/or AI security (e.g., privacy, robustness)

Main Duties:

• Independently reproduce open-source SOTA methods (e.g., set up virtual environments, replicate training/evaluation pipelines), understand codebases, and read related papers.
• Develop and improve method frameworks under guidance; select and test new datasets; and produce clear, reproducible experiment reports.
• Plan and execute work efficiently with good time management, communicate progress promptly, and collaborate effectively with the team.
• Uphold high standards of research integrity.

Duration: 6 months

Stipend: $1,500 per month

Informal enquiries are greatly welcome and can be directed to Dr Viktor Schlegel v.schlegel@imperial.ac.uk.

Questions about the recruitment process, should go to the HR at Imperial Global Singapore hrigsingapore@imperial.ac.uk.