Autonomous Vulnerability Research (Harness Engineering) Lead in Bristol

Salary Range: £92,701 - £109,060

We support flexible working – click here for more information on flexible working options.

Flexible Working Options: Hybrid Working, Job Share

LOCATION(S): Bristol, Leeds, Edinburgh, Manchester, London

HOURS: Full-time

WORKING PATTERN: Our work style is hybrid, which involves spending at least two days per week, or 40% of our time, at one of our office sites.

About this opportunity:

We're establishing a new Autonomous Vulnerability Research (Harness Engineering) Team with a strong mission: to build the Group's agentic vulnerability research platform, enabling AI-powered vulnerability discovery, exploit validation, risk prioritisation, and remediation verification at unprecedented scale and speed. This team will sit at the intersection of offensive security, artificial intelligence, software engineering, and security research. By employing frontier AI models, autonomous agents, testing frameworks, and sophisticated security tooling, the team will create a continuously evolving capability that accelerates vulnerability research, strengthens defensive resilience, and enables the Group to remain ahead of rapidly changing threat landscapes.

As the Autonomous Vulnerability Research (Harness Engineering) Lead, you will define the vision, recruit and grow a multidisciplinary engineering team, and own the development of the Group's AI-powered vulnerability research platform. You will shape how offensive security is delivered in the future by combining autonomous systems with human guidance to create a scalable, resilient, and continually improving security capability.

What you’ll be doing:

• Build and own the Autonomous Vulnerability Research (Harness Engineering) Team, defining strategy, operating model, standards, and roadmap.
• Design and deliver LBG's agentic vulnerability research harness and supporting platform services.
• Develop autonomous workflows for vulnerability discovery, validation, prioritisation, remediation recommendation, and remediation verification.
• Integrate frontier AI models, security tooling, and engineering workflows into a scalable research platform.
• Establish evaluation, observability, governance, and safety controls to ensure credible outcomes.
• Partner with Offensive Security, AI Security, Engineering, and Architecture teams to operationalise research and accelerate remediation.
• Drive innovation in AI-assisted vulnerability research and ensure the capability remains aligned to emerging industry practices.

What we’re looking for:

• Experience leading engineering, security research, offensive security, or platform engineering teams.
• Experience building AI-powered security tooling, agentic systems, or autonomous testing platforms.
• Strong understanding of AI systems, LLMs, agentic architectures, and AI evaluation techniques.
• Deep knowledge of vulnerability research, penetration testing, application security, or exploit development.
• Experience building software platforms, automation frameworks, or large-scale security tooling.
• Strong software engineering skills (Python, Go, Rust, Java, or similar).
• Expertise in cloud-native architectures, distributed systems, APIs, and platform engineering.
• Experience translating modern research into production-ready capabilities.
• Consistent track record of building new teams and capabilities from inception and delivering measurable outcomes.
• Excellent partner management and influencing skills.

And any of these would be great:

• Experience contributing to vulnerability research, security tooling, or open-source projects.
• Cyber security related qualifications or trainings.
• MSc or PhD in Computer Science, Cyber Security, Artificial Intelligence, Machine Learning, or related discipline.
• Knowledge of AI red teaming, LLM security testing, or adversarial machine learning.
• Experience operating within highly regulated environments such as financial services.

We know that great talent comes from many backgrounds. Whilst this job advert may reference specific years of experience, we recognise that skills are developed in many ways, so if you have relevant, transferable experience, we encourage you to apply.

This is a place for you. We offer reasonable workplace adjustments for colleagues with disabilities, including flexibility in office attendance, location and working patterns. And, as a Disability Confident Leader, we guarantee interviews for a fair and proportionate number of applicants who meet the minimum criteria for the role with a disability, long-term health or neurodivergent condition through the Disability Confident Scheme.

We also offer a wide-ranging benefits package, which includes:

• A generous pension contribution of up to 15%
• An annual performance-related bonus
• Share schemes including free shares
• Benefits you can adapt to your lifestyle, such as discounted shopping
• 30 days’ holiday, with bank holidays on top
• A range of wellbeing initiatives and generous parental leave policies

Like what you hear? Join us!

At Lloyds Banking Group, we're driven by a clear purpose; to help Britain prosper. Across the Group, our colleagues are focused on making a difference to customers, businesses and communities. With us you'll have a key role to play in shaping the financial services of the future, whilst the scale and reach of our Group means you'll have many opportunities to learn, grow and develop.

We keep your data safe. So, we'll only ever ask you to provide confidential or sensitive information once you have formally been invited along to an interview or accepted a verbal offer to join us which is when we run our background checks. We'll always explain what we need and why, with any request coming from a trusted Lloyds Banking Group person.

We're focused on creating a values-led culture and are committed to building a workforce which reflects the diversity of the customers and communities we serve. Together we’re building a truly inclusive workplace where all of our colleagues have the opportunity to make a real difference.