Job Summary
The Ethical and Trustworthy AI Group at CFAR advances the scientific foundations for AI systems and frameworks that are fair, transparent, safe, and aligned with human values across cultures, modalities, and deployment contexts.
We are seeking a Research Scientist with a strong background in computer science and artificial intelligence. You will lead original AI research while working across disciplines to study the social, cultural, and safety dimensions of advanced agentic AI systems. The role will focus on one or more of the following areas:
Core Research Directions
• Value Alignment of Foundation Models — preference learning, alignment methods, and evaluation across modalities, cultures, and contexts
• Interpretability and Explainability — mechanistic interpretability, emergent-behavior analysis, and transparency in frontier language models and agentic systems
• Human-Centered AI and Interaction — behavioral and cognitive effects of human–AI synergy, socially aware communication, and multi-agent collaboration
• Societal Impact and AI Governance — measuring AI’s effects on societal values, institutional trust, and decision-making at scale
What You Will Do
- Lead original research and publish at top-tier venues such as NeurIPS, ICML, ICLR, ACL, CHI, and AAAI
- Design and conduct experiments involving foundation models, agentic systems, data benchmarks, and evaluation methods
- Work with researchers in machine learning, NLP, HCI, social science, and ethics to address interdisciplinary research questions
- Engage with industry and government partners to translate research findings into practical applications and policy-relevant outcomes
- Mentor junior researchers and contribute to research proposals and grant applications, where appropriate
Who We Are Looking For
- PhD in Computer Science, Artificial Intelligence, NLP, or a closely related technical field
- Strong publication record at leading AI, machine learning, NLP, or HCI venues
- Hands-on experience with large language models, agentic AI systems, and LLM adaptation and optimization
- Experience designing experiments and evaluations for advanced AI systems, and strong interest in AI research in relation to human behavior, cultural diversity, and societal impact
- Ability to define research problems independently, lead projects, and collaborate across disciplines