Key ResponsibilitiesDesign and implement safety architectures for Agentic AI systems, including guardrails, reward modeling, and selfāmonitoring capabilitiesLead and collaborate on alignment techniques such as inverse reinforcement learning, preference learning, interpretability tools, and humanāinātheāloop evaluationDevelop continuous monitoring strategies for agent behavior in both simulated and realāworld environmentsPartner with product, legal, Responsible AI, governance, and deployment teams to ensure responsible scaling and deploymentContribute to and publish novel research on alignment of LLMābased agents, multiāagent cooperation/conflict, or value learningProactively identify and mitigate failure modes, e.g., goal misgeneralization, deceptive behavior, unintended instrumental actionsSet safety milestones for autonomous capabilities as part of deployment readiness reviewsTechnical SkillsProficiency in SQL, Python, and data analysis/data mining tools. Experience with machine learning frameworks like PyTorch, JAX, ReAct, LangChain, LangGraph, or AutoGenExperience with high performance, largeāscale ML systemsExperience with deploying or auditing LLMābased agents or multiāagent AI systemsExperience with largeāscale ETLUse your skills to make an impactRequired QualificationsMaster's Degree and 4+ years of experience in research/ML engineering or an applied research scientist position preferably with a focus on developing productionāready AI solutions2+ years of experience leading development of AI/ML systemsDeep expertise in AI alignment, multiāagent systems, or reinforcement learningDemonstrated ability to lead researchātoāproduction initiatives or technical governance frameworksStrong publication or contribution record in AI safety, interoperability, or algorithm ethicsPreferred QualificationsPh.