Research Associate in Private and Trustworthy AI: Information-Theoretic Foundations

Research Associate in Private and Trustworthy AI: Information-Theoretic Foundations

Full-Time 50733 - 59484 £ / year (est.) On-site
O

At a Glance

  • Tasks: Lead groundbreaking research in Private and Trustworthy AI, tackling real-world challenges.
  • Company: Join Imperial College London, a world-leading institution in cutting-edge technology.
  • Benefits: Enjoy a competitive salary, generous leave, and access to GPU resources.
  • Other info: Collaborative environment with opportunities for career growth and mentorship.
  • Why this job: Make a significant impact on AI trustworthiness while developing your own research agenda.
  • Qualifications: PhD in relevant fields or nearing completion; strong programming skills required.

The predicted salary is between 50733 - 59484 £ per year.

Imperial College London seeks a Research Associate in Private and Trustworthy AI to join the INFORMED-AI Hub. This full-time postdoctoral role focuses on information-theoretic foundations for generative models, addressing challenges like watermarking, machine unlearning, and privacy-preserving training. The position offers a salary of £50,733 - £59,484 per annum and is funded for up to 24 months, starting January 2027.

Candidates must hold or be close to completing a PhD in electrical engineering, computer science, mathematics, or statistics.

Key responsibilities include:

  • Leading original research
  • Developing provable algorithms
  • Publishing in top venues
  • Collaborating with partners at the University of Bristol

The role provides access to GPU resources, conference travel budgets, and career support. Visa sponsorship is available. Applicants should submit a CV, publication list, research statement, and representative papers.

We are seeking a postdoctoral researcher to tackle questions such as how to design a watermark that survives editing or paraphrasing, what it means for a model to have 'forgotten' a training example, and the utility cost of preventing a model from leaking its training data. The aim is to bring the tools of information and coding theory to enable trustworthiness of modern generative models and to turn the resulting insights into practical algorithms.

Potential research directions include:

  • Watermarking and provenance for LLMs and diffusion models
  • Machine unlearning
  • Privacy-preserving training and inference

This in-person postdoctoral position is based at Imperial College’s South Kensington Campus in London, UK, and is funded for up to 24 months, starting in January 2027 or as soon as possible thereafter. The Research Associate will be supervised by Prof. Deniz Gunduz within the Electrical and Electronic Engineering Department at Imperial College London.

What you would be doing:

  • Shaping and leading your own research agenda
  • Undertaking original research of international excellence
  • Developing fundamental theory with provable guarantees
  • Writing reports for submission to research sponsors
  • Presenting findings at international conferences
  • Publishing in leading venues in information theory, machine learning and security
  • Collaborating with researchers at the University of Bristol and across the Hub
  • Helping mentor PhD students

What we are looking for:

Education: Hold a PhD (or be close to completion) in electrical engineering, computer science, mathematics, statistics, or a related field.

Experience: Practical experience within a research environment and/or a track record of publications at leading venues. Strong expertise in one or more of the following: programming in Python and deep learning frameworks (e.g., PyTorch or JAX). Desirable: prior work on watermarking, machine unlearning, differential privacy, membership inference or memorisation; hands-on experience with LLMs or diffusion models.

Knowledge: Knowledge and research experience in one or more of the following areas: information theory, coding theory, learning theory, privacy, optimisation, and generative models.

Skills and Abilities: Ability to conduct a detailed review of recent literature, develop and apply new concepts, creative approach to problem-solving, excellent verbal and written communication skills.

What we can offer you:

  • The opportunity to continue your career at a world-leading institution
  • The opportunity to interact and collaborate with researchers across the INFORMED-AI Hub
  • Joint supervision across Imperial and Bristol, with funded research visits
  • Sector-leading salary and remuneration package
  • Be part of a diverse, inclusive and collaborative work culture

Please note that job descriptions cannot be exhaustive, and the post-holder may be required to undertake other duties, which are broadly in line with the above key responsibilities.

Research Associate in Private and Trustworthy AI: Information-Theoretic Foundations employer: Opportunita

Opportunita is an attractive employer due to its commitment to research excellence and professional development. Faculty members benefit from a collaborative work environment and opportunities to engage with industry partners, enhancing their academic careers.

O

Contact Details:

Opportunita Recruitment Team

We think you need these skills to ace Research Associate in Private and Trustworthy AI: Information-Theoretic Foundations

PhD in electrical engineering, computer science, mathematics, or statistics
Research experience in information theory
Knowledge of coding theory
Understanding of learning theory
Expertise in privacy and optimisation
Experience with generative models (e.g., LLMs and diffusion models)
Programming in Python