The role
G-Research develops and operates advanced research platforms and machine learning infrastructure at scale, with AI embedded across research and engineering functions. As a Principal AI Security Engineer you will provide firm‑wide technical leadership for AI security across the full lifecycle. Reporting to the Head of Security, you will act as the senior technical authority for AI security at G‑Research. You will work across research engineering, platform engineering, security and risk teams to define and implement security controls that protect AI systems without constraining innovation. As a principal‑level individual contributor, you will shape technical direction, define design patterns and influence firm‑wide decisions on AI risk, resilience and governance.
Key responsibilities of the role include:
AI system security leadership
- Defining and driving the firm‑wide approach to securing AI systems across the model lifecycle
- Identifying systemic AI‑specific risks, including model integrity, prompt injection and misuse
- Establishing secure design principles that enable experimentation while maintaining strong controls
Securing AI‑enabled engineering and autonomy
- Providing technical leadership on securing AI‑assisted development and autonomous workflows
- Defining guardrails, integrity controls and standards for integrating AI services into engineering and operational platforms
Identity, integrity and logging
- Designing robust identity and access models for AI systems, including service authentication role‑based restrictions
- Ensuring integrity of models, data and pipelines, with strong logging and audit mechanisms
Cross‑functional influence and governance
- Working with senior stakeholders across engineering, security, research and risk to translate AI risks into actionable controls
- Contributing to firm‑wide AI governance, risk and control strategy
Technical depth and hands‑on contribution
- Leading design reviews, threat modelling and targeted implementation for critical AI initiatives.
- Raise technical standards and mentor senior engineers on AI‑related security challenges
Who are we looking for?
We are looking for an exceptional security engineer with deep expertise in both security engineering and AI systems. The ideal candidate will have the following skills and experience:
- Securing large‑scale software or ML systems in production
- Expertise in AI or ML security, including model integrity, adversarial threats and supply chain risk
- Strong understanding of modern ML architectures, training workflows and inference infrastructure
- Excellent engineering fundamentals with ability to engage with complex systems and code
- Proven ability to influence technical direction through collaboration and evidence
Why join us?
- Highly competitive compensation plus annual discretionary bonus
- Lunch provided (via Just Eat for Business) and dedicated barista bar
- 30 days' annual leave
- 9% company pension contributions
- Informal dress code and excellent work/life balance
- Comprehensive healthcare and life assurance
- Cycle‑to‑work scheme
- Monthly company events
G-Research is committed to cultivating and preserving an inclusive work environment. We are an ideas‑driven business and we place great value on diversity of experience and opinions.
We want to ensure that applicants receive a recruitment experience that enables them to perform at their best. If you have a disability or special need that requires accommodation please let us know in the relevant section.
#J-18808-Ljbffr