AI Safety Researcher – NeGD
Quick Info
- Vacancies
- Vacancies: 1
- Qualification
- Qualification: Candidates must possess a B.Tech./B.E. or M.Tech./M.S./M.Sc. in Computer Science, Information Security, AI/ML, or a related quantitative discipline. An 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.
- Experience Required
- Experience Required: Minimum 6 years of total experience in ML, applied AI, security research, or a closely related discipline, with at least 3 years specifically in adversarial ML, AI red teaming, LLM safety evaluation, or AI/ML security research. Demonstrable hands-on LLM red-teaming experience and adversarial ML work are essential.
- Application Mode
- Application Mode: Apply Online
- Deadline
- Deadline:
NeGD is seeking an AI Safety Researcher, with one vacancy, to design and execute adversarial attack campaigns and develop robust AI systems. This role offers a competitive pay package for professionals with a B.Tech./B.E. or M.Tech./M.S./M.Sc. in Computer Science or a related quantitative discipline, who are passionate about ensuring the safety and ethical deployment of AI. It's a unique opportunity to contribute to critical research in adversarial ML, AI red teaming, and LLM safety evaluation within a government context.
- The role involves designing and executing adversarial attack campaigns against various AI models and systems.
- Candidates will develop and maintain a reusable adversarial ML attack library and test harness for pre-production evaluation.
- Producing adversarial-robustness reports with quantitative measures and prioritised mitigation guidance is a key responsibility.
- Leading structured red-team exercises against LLM, RAG, and agentic AI deployments across the program is essential.
- Applicants should have a minimum of 3 years of experience specifically in adversarial ML, AI red teaming, LLM safety evaluation, or AI/ML security research.
applyforgovt.com is an independent informational platform and is not affiliated with any government organization, PSU, ministry, department, or recruiting authority. Verify details on the official website before applying.
Additional Salary Information
Refer official detailed notification
Important Dates
Selection Process
Screening of applications based on qualifications, age, and relevant experience.
Shortlisted candidates will be invited for interviews.
Application Fees
Refer official detailed notification
Reservation
Refer official detailed notification
How to Apply
- Eligible candidates must apply ONLINE through the official application portal.
- Ensure all required documents, including educational qualifications, experience certificates, and age proof, are ready for upload.
- The application deadline is November 13, 2026. Candidates are advised to apply well in advance to avoid last-minute technical issues.
Frequently Asked Questions
The salary for the AI Safety Researcher position is not explicitly mentioned in the notification. Candidates are advised to refer to the official detailed notification for pay scale information.
Candidates for the AI Safety Researcher role must hold a B.Tech./B.E. or M.Tech./M.S./M.Sc. in Computer Science, Information Security, AI/ML, or a related quantitative discipline. An advanced degree with a thesis or published work in adversarial ML, AI security, LLM safety, or Responsible AI is highly desirable.
The maximum age limit for the AI Safety Researcher position is 55 years on the closing date of application.