Find your next role
Discover amazing opportunities across our network of companies committed to gender equality in the workplace.
Introduction
AI systems with embedded large language models (LLMs), like AI Agents, demonstrate significant potential for solving complex tasks by dynamically adapting to feedback and refining their strategies. However, ensuring responsible, safe, and secure deployment is crucial, as these systems face privacy and security risks from malicious actors – be it leakage of confidential information, or injections for adversarial behaviour.
This project will focus on systematically analysing threat models, attack surfaces, and exploitation techniques (red-teaming) to identify critical risks in industrial contexts and develop effective defences (blue-teaming). This is key to building trustworthy systems for the future.
Your role and responsibilities
This is a fully funded 4-year PhD position at the intersection of AI and Security as part of a new initiative between IBM Research Europe and Trinity College Dublin (TCD).
The selected student will be registered at TCD and employed by IBM for the duration of the PhD with the following benefits:
* Access to resources and expertise at IBM Research and TCD
* A substantial PhD salary (>40,000 euro per annum)
* TCD PhD program fees (EU or non-EU level) fully funded
Required education
Bachelor's Degree
Preferred education
Master's Degree
Required technical and professional expertise
- A degree in computer science, applied mathematics, engineering or similar.
- Basics of Machine Learning and AI: knowledge of ML fundamentals.
- Programming skills: Python, version control, ability to write complex code from scratch and extend existing code.
- Interest in performing research - including evaluation of existing literature, ideation, authoring research publications.
- Ability to move quickly from idea to software prototype for evaluation and demonstration.
- Excellent spoken and written English.
Preferred technical and professional experience
- Knowledge of GenAI approaches: model architectures, fine-tuning, transfer learning.
- Advanced programming skills: Python, data preprocessing (pandas), experience with AI/ML libraries such as Pytorch is beneficial.
- Previously published academic papers.