Research Scientist, AI Safety - Global Frontier Tech Recruitment Program - 2027 Start (PhD)

Research and evaluate AI safety for foundation models and agent-based applications by developing adversarial testing, evaluation methods, benchmarks, and toolchains. Help build risk-defense technologies and trustworthy runtime security assurance for agent deployments. Contribute to secure training and inference approaches that protect data and model assets, improving the confidentiality, performance, and safety of the end-to-end defense system for LLM business lines.