• Design and implement safety architectures for Agentic AI systems, including guardrails, reward modeling, and self-monitoring capabilities • Lead and collaborate on alignment techniques such as inverse reinforcement learning, preference learning, interpretability tools, and human-in-the-loop evaluation • Develop continuous monitoring strategies for agent behavior in both simulated and real-world environments • Partner with product, legal, Responsible AI, governance, and deployment teams to ensure responsible scaling and deployment • Contribute to and publish novel research on alignment of LLM-based agents, multi-agent cooperation/conflict, or value learning • Proactively identify and mitigate failure modes, e.g., goal misgeneralization, deceptive behavior, unintended instrumental actions • Set safety milestones for autonomous capabilities as part of deployment readiness reviews