AI Security Researcher — Adversarial ML & High-Assurance

CommonAI Holdings Ltd; Cambridge; Remote; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Competitive salary package

Pension

Professional development opportunities

Networking opportunities

Job summary

CommonAI CIC invites an AI Security Researcher to join our High Assurance team in Cambridge. You’ll think like an attacker to test AI systems, focusing on attacks, defenses, and auditing simpler models in regulated contexts.

You will track developments, produce briefings, red-team within scope, and help build interpretable methods while sharing insights across Members and colleagues. Our office is a vibrant space near Cambridge station, offering a collaborative environment, professional growth,

Qualifications

• Proven experience in security research, offensive security or adversarial machine learning.
• Strong understanding of how modern AI systems work, including training, deployment and serving.
• Familiarity with attacks on AI systems (e.g. jailbreaks, prompt injection, data poisoning, backdoors, model extraction).
• Strong Python, and the ability to build your own tools and experiments.
• Excellent written communication: translate complex findings for technical and non-technical readers.
• Judgement and confidence to challenge technical decisions constructively.
• Enthusiasm for using LLMs, coding assistants, and agents in software development.

Responsibilities

• Track key research and developments relevant to the High Assurance programme, including attacks on AI models, defences against them, and the security of the systems that serve them.
• Report on what these developments mean for the programme and our Members, through written briefings and presentations.
• Review the programme's technical decisions and directions from an attacker’s point of view, and propose stronger alternatives.
• Threat-model AI systems used in regulated settings, covering model weights, training data, inference serving, and the tools and agents built on them.
• Red-team the systems we build, within an agreed scope, and report findings through a clear disclosure process.
• Help develop interpretability methods for the simpler models produced by our frontier research, and test their limits, for example by trying to hide behaviour the methods should detect.
• Build internal expertise by sharing what you learn with colleagues and helping answer technical questions from our Members.

Skills

Security research

Adversarial ML

Penetration testing

Threat modelling

Technical writing

Communication

LLMs / AI tools

Education

PhD in security or ML or related

Tools

Penetration testing tools

Adversarial ML frameworks

Job description

CommonAI CIC invites an AI Security Researcher to join our High Assurance team in Cambridge. You’ll think like an attacker to test AI systems, focusing on attacks, defenses, and auditing simpler models in regulated contexts.

You will track developments, produce briefings, red-team within scope, and help build interpretable methods while sharing insights across Members and colleagues. Our office is a vibrant space near Cambridge station, offering a collaborative environment, professional growth,