
Lead Engineer/Engineer, AI R&D (AI Safety and Security), xCyber
Home Team Science and Technology Agency
- Singapore
- Permanent
- Full-time
- Assess, develop, deploy and provide guidance on security measures to reinforce the security of AI models and AI-driven applications. • Develop procedures on operating defences to mitigate adversarial AI threats. • Conduct red team exercises to emulate real-word adversarial attacks on AI models and AI-driven applications. • Generate adversarial test cases and improve robustness. • Evaluate red teaming tools, build and automate adversarial attack workflows. • Research emerging adversarial AI threats and potential impacts. • Work with application teams, data scientists and security teams to identify new vulnerabilities, detection mechanisms or mitigating controls.
- 0-2 years in relevant field. • Applicants with no prior experience are welcome to apply. • Cyber Security professional qualifications such as CISSP or offensive security certification is preferred. • Ability to multi-task whilst working under extreme pressure with tight deadlines. • Meticulous in planning. • Able to work independently and as a team. • Able to cope with a reasonably high level of stress. • Demonstrate resiliency, drive and level headedness. • Good interpersonal and communications skills for internal/external stakeholder engagement. All new hires are appointed on a two-year contract in the first instance and will be assessed and considered for permanent tenure over time, based on performance. As part of the shortlisting process for this role, you may be required to complete a medical declaration and/or undergo further assessment. All applicants will be updated on the status of their applications within 4 weeks upon closing of the advertisement.