Applied Research Intern - AI Safety Security - Global Frontier Tech Recruitment Program - 2027 Start (PhD)

What you'll do

• Develop attack-defense detection and evaluation methods, benchmarks, and toolchains for multimodal foundation models and agents.
• Research risk defenses and runtime security for agent applications, and training and inference methods that protect data and model assets.
• Help build and optimize confidential training and inference infrastructure for foundation models.

What they ask for

• Currently pursuing a PhD in Computer Science or a related discipline.
• Excellent theoretical and practical knowledge of LLMs and foundation models.
• Strong publication record at leading conferences, such as NeurIPS, ICML, ICLR, ACL, or EMNLP.
• Excellent coding ability, knowledge of data structures and fundamental algorithms, and proficiency in Python, Go, or Java.

Nice to have

• Competition wins (e.g., ACM/ICPC, USACO/NOI/IOI, Top Coder, or Kaggle).
• Communication and collaboration skills; software engineering, NLP, or deep learning experience; creativity and problem-solving ability.

Tools

LLM, foundation models, Python, Go, Java

AI focus

AI safety and security research for foundation models and agents, including adversarial testing, evaluation, runtime defenses, and secure training and inference.