Overview
In this role you will design and enhance a GenAI prompt security platform to safeguard AI/LLM-based applications, build automated security testing for diverse use cases, and own scalable security solutions. You will collaborate with engineering, operations, and partner teams to embed security across Citi’s GenAI initiatives. The work combines security and engineering excellence to defend against adversarial prompts while supporting rapid, reliable AI deployments. This is a mission-driven opportunity to shape secure GenAI capabilities at scale.
Pay / Benefits
- 27 days annual leave
- discretionary annual performance related bonus
- Private Medical Care
- Life Insurance
- Pension Plan
- Paid Parental Leave
Responsibilities
- Design, develop, and optimize a GenAI prompt security platform to defend AI/LLM apps from adversarial attacks and prompt injections
- Build and automate a security testing framework to validate protection mechanisms for various LLM use cases
- Own solutions that operate at scale across the organisation
- Collaborate with Engineering, Operations, and partner teams across Citi and time zones
Key requirements
- Bachelor’s degree or equivalent work experience
- Strong programming experience in Python and/or Go
- Experience with designing and implementing secure APIs and libraries
- Experience in full lifecycle of enterprise software solutions with cross-functional collaboration
- Experience with containerized deployment (Kubernetes, OpenShift)
- DevOps/CI-CD experience and agile methodologies
- Knowledge of Generative AI/LLM frameworks and adversarial testing is a plus
- Experience in Cyber engineering/Operations (DevSecOps or MLSecOps) and system architecture design
- self-starter
- excellent interpersonal and problem-solving skills
- strong oral and written communication
- Python
- Go
- Git
…
