Research Scientist Intern - Security for AI

What you'll do

• Design and develop security solutions for Large Language Models against threats like prompt injections and data disclosure.
• Conduct security risk assessments and recommend mitigations for LLM vulnerabilities.
• Stay current on AI risks and emerging technologies to strengthen product security.
• Collaborate with external organizations on AI security best practices and advancements.

What they're looking for

• Currently pursuing PhD in Computer Science or related field.
• Strong publication record at top-tier conferences like NeurIPS, ICML, ICLR, ACL, EMNLP.
• Excellent knowledge of LLM and foundation model theory and practice.
• Prior experience in software engineering, NLP, or deep learning preferred.

Pay and perks

• $60 hourly rate.
• Day one health insurance, life insurance, and wellbeing benefits.
• 10 paid holidays yearly and paid sick time.
• Housing allowance eligible for non-remote positions.