Security Researcher (AI)

TL;DR

Security Researcher (AI): Investigating threats and designing defenses for generative AI technologies with an accent on model security, prompt injection, and agentic systems. Focus on building robust detection mechanisms and collaborating with engineering teams to ensure the safety and trustworthiness of next-generation AI platforms.

Location: Must be based in the UK and able to work from the Cambridge office 2 days per week

Company

hirify.global is a global leader in AI for cybersecurity, providing a platform that protects nearly 10,000 organizations from unknown threats using proprietary AI technologies.

What you will do

• Investigate emerging trends in generative AI compliance and visibility.
• Research attacker tradecraft targeting generative AI chatbots and agentic architectures.
• Create, validate, and test new security detections in a research environment.
• Collaborate with product, development, and machine learning teams to integrate security insights.
• Provide detailed feedback on the performance and safety of AI product features.

Requirements

• Must be able to work hybrid from the Cambridge office, UK
• Familiarity with the generative AI landscape, foundation models, and agentic architectures.
• Knowledge of attacker methodologies such as prompt injection, data poisoning, and extraction attacks.
• Strong logical reasoning and problem-solving skills in complex environments.
• Clear communication skills for both technical and non-technical stakeholders.

Culture & Benefits

• 23 days of holiday plus public holidays, increasing to 25 days after 2 years.
• Private medical insurance for employee, partner, and children.
• Life insurance policy at 4 times base salary.
• Salary sacrifice pension scheme.
• Enhanced family leave and confidential Employee Assistance Program.
• Birthday day off and cycle to work scheme.