NeGD AI Safety Researcher Recruitment 2026 – Apply Online

Last date: 13 November 2026 Vacancies: 1 How to apply: Online Fee: No application fee is mentioned in the notification Place: Delhi

The official notification gives the full conditions for the post, including anything not covered in the tables on this page. Read it before applying. The download link is in the Important Links table below. Download NeGD notification PDF FREEJOBALERT DAILY QUIZ Preparing for Govt Exams? Test Yourself! 25 Questions · 20 Minutes · Instant Score Take Today's Free Quiz →

Qualification: B.Tech./B.E. or M.Tech./M.S./M.Sc. in Computer Science, Information Security, AI/ML, or a related quantitative discipline Advanced degree (M.Tech./M.S./Ph.D.) with a thesis or published work in adversarial ML, AI security, LLM safety, or Responsible AI is highly desirable Certifications (Desirable): OSCP, GWAPT or CEH combined with demonstrable AI/ML security work; DeepLearning.AI or equivalent ML foundations; MLSecOps or LLMsecurity specialist certifications where available Non-traditional backgrounds with demonstrable adversarial ML research, published safety work, credible LLM red-team disclosures, or CTF/red-team achievements will be considered in lieu of formal qualification

The responsibilities for the AI Safety Researcher position include: Design and execute adversarial attack campaigns - evasion, model inversion, membership inference, model extraction, data poisoning - against pod deliverables including document intelligence, predictive-analytics and fraud-scoring models, and visual AI, face-embedding and liveness models. Develop and maintain a reusable adversarial ML attack library and test harness for repeatable pre-production evaluation. Produce adversarial-robustness reports for each pod service with quantitative measures, reproducible attack notebooks, and prioritised mitigation guidance. Lead structured red-team exercises against LLM, RAG and agentic AI deployments across the programme, covering prompt injection, jailbreaks, indirect prompt injection via retrieved documents, data exfiltration, unsafe tool invocation, sandbox escape and policy-bounda

Contractual basis, initially for a period of three years, with possible extensions based on project requirements.