Designing, developing, optimizing, and enhancing a GenAI prompt security platform to protect firm AI/LLM-based applications from adversarial attacks and prompt injections.
Building and automating a security testing framework to validate protection mechanisms for various LLM use cases.
Owning solutions that are expected to operate and perform at scale across the organisation.
Collaboration with multiple stakeholders and partners across Engineering and Operations as well as partner teams within the wider Citi organisation, across different time zones.
Job Skills/ Qualifications:
Highly motivated self-starter with excellent interpersonal and problem-solving skills
Bachelor's degree or equivalent work experience
Good oral and written communication skills
7+ years of relevant industry work experience
Experience of the full lifecycle of design, implementation and running of enterprise software solutions involving cross functional team collaboration
Expertise in a major programming language such as Python and/or Go, and associated tooling (Git, Maven, IDEs, Jenkins etc)
Expertise in designing and implementing secure APIs and libraries.
Experience in Generative AI, LLM frameworks, LLM prompt engineering and/or adversarial testing is a bonus.
Experience with Cyber engineering and Operations, which could include DevSecOps or MLSecOps.
Experience contributing to the architecture and design (architecture, design patterns, reliability, scaling) of new and current systems
Experience in containerized deployment (Kubernetes, OpenShift etc)