AI Security Researcher: Red Teaming for High-Assurance AI

CommonAI C.I.C.; Cambridge; Vor Ort; GBP 70.000 - 90.000; Vollzeit

Benefits dieser Stelle

Competitive salary package and pension

Professional development opportunities

Networking with tech, finance and acad

Vibrant Cambridge office near train st

Zusammenfassung

CommonAI CIC is seeking an AI Security Researcher to probe AI systems with an attacker mindset, focusing on safety, explainability, and accountability for regulated environments. You will track research, test defenses, and report findings to support a High Assurance programme.

You will threat-model AI systems, red-team the platforms, and help develop interpretable models while sharing insights with colleagues and Members across finance and academia. Cambridge office-based role.

Qualifikationen

• Proven experience in security research, offensive security or adversarial ML
• Strong understanding of how modern AI systems work
• Familiarity with attacks on AI systems (e.g. jailbreaks, prompt injection, data poisoning)
• Strong Python and ability to build your own tools and experiments
• Excellent written communication: you can turn complex technical findings into clear briefings for technical and non-technical readers
• The judgement and confidence to challenge technical decisions constructively
• A strong enthusiasm for using LLMs, coding assistants, and agents as core tools in your own software development process

Aufgaben

• 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

Kenntnisse

Security research

Adversarial ML

Python

Written communication

Attack mindset

Ausbildung

PhD or equivalent in security/ML

Jobbeschreibung

CommonAI CIC is seeking an AI Security Researcher to probe AI systems with an attacker mindset, focusing on safety, explainability, and accountability for regulated environments. You will track research, test defenses, and report findings to support a High Assurance programme.

You will threat-model AI systems, red-team the platforms, and help develop interpretable models while sharing insights with colleagues and Members across finance and academia. Cambridge office-based role.