Senior AI Security Engineer, Citi

Citi

Location:
United Kingdom, London

Category:
IT - Software Development

Contract Type:
Not provided

Salary:

Not provided

Save Job

Apply Position

Job Description:

Senior AI Security Engineer role in Citi's Application, Platform and Engineering team, focused on shaping the tech and engineering strategy for the entire bank. The team works with modern technologies including generative AI, cloud, security, modern app stacks with Golang, open source and Kubernetes ecosystem. The role involves securing AI applications at scale and working on cutting-edge security problems.

Job Responsibility:

Build secure AI products from 0-1 - Engineer production-grade, business-facing AI platforms with security built-in from day one
Conduct ethical hacking and red team activities - penetration testing, vulnerability research, and attack simulation
Design and build security tools and frameworks - Create automated security solutions that scale across fast-paced development cycles
Secure novel AI attack surfaces - Identify and mitigate LLM-specific vulnerabilities, prompt injection attacks, and AI model security risks
Lead 'shift left' security - Embed security practices throughout rapid development lifecycle while maintaining velocity
Mentor security practices - Guide other engineers on secure coding, vulnerability remediation, and security-first thinking

Requirements:

Production system builder with security focus - proven track record of architecting and building secure, large-scale production applications and business-facing platforms from the ground up
Ethical hacking and penetration testing expertise - hands-on experience finding and exploiting vulnerabilities, conducting red team exercises
State-of-the-art security engineering with Go, Python, JavaScript
HashiCorp Vault mastery - deep experience writing custom plugins, creating secrets engines, implementing dynamic credentials
Enterprise authentication & authorization - designing and implementing OAuth, JWT, RBAC, and complex identity systems
API security and threat modelling - securing REST/GraphQL APIs, conducting threat assessments
AI/ML security and vulnerability research - understanding of LLM vulnerabilities, model security, prompt injection attacks
Security automation and tooling – automating manual security processes
Cloud-native security - securing containerized applications in Kubernetes, service mesh security
Incident response and forensics - experience investigating, analyzing, and responding to security incidents

Nice to have:

Experience with generative AI projects utilising LLMs showing complex and clever architectures or systematic evaluation of an LLM's behaviour
Thriving in results-driven environment where flexibility fuels impact
Being a game-changer ready to step beyond designated role
Enjoying pair programming
Relentless passion to learn more about AI security, LLM attacks

What we offer:

27 days annual leave (plus bank holidays)
Discretional annual performance related bonus
Private Medical Care & Life Insurance
Employee Assistance Program
Pension Plan
Paid Parental Leave
Special discounts for employees, family, and friends
Hybrid working model (up to 2 days working at home per week)
Competitive base salary (annually reviewed)

Additional Information:

Job Posted:
November 26, 2025

Employment Type:

Fulltime

Work Type:

Hybrid work

View All Jobs In This Company

Job Link Share:

Senior AI Security Engineer