Student Researcher [Seed - Model Evaluation] - 2026 Start (PhD)

Descrizione del lavoro:

Established in 2023, the ByteDance Seed team is dedicated to discovering new approaches to general intelligence, and pushing the boundaries of AI. Our research spans large language models, speech, vision, world models, AI infrastructure, next-generation interfaces and more. With a long-term vision and determination in AI, the ByteDance Seed team remains committed to foundational research. We aim to become a world-class AI research team that drives real technological progress and delivers societal benefits. We are looking for talented individuals to join us for an internship in 2026. PhD Internships at ByteDance aim to provide students with the opportunity to actively contribute to our products and research, and to the organization's future plans and emerging technologies. PhD internships at ByteDance provide students with the opportunity to actively contribute to our products and research, and to the organization's future plans and emerging technologies. Our dynamic internship experience blends hands-on learning, enriching community-building and development events, and collaboration with industry experts. Applications will be reviewed on a rolling basis - we encourage you to apply early. Please state your availability clearly in your resume (Start date, End date). Responsibilities: - Explore the intrinsic consistency of foundation models across pre-training and post-training stages, and help characterize their capability ceilings. - Design evaluation protocols grounded in model internal mechanisms, with a focus on interpretability and failure analysis. - Develop novel benchmarks and testing paradigms to systematically evaluate models. - Contribute to defining evaluation standards for next-generation intelligent systems, including Agent Foundation Models and long-horizon research agents

Requisiti del candidato:

Minimum Qualifications: - Currently pursuing a PhD in Machine Learning, Artificial Intelligence, or a related field. - Strong analytical mindset and ability to reason from first principles. - Demonstrated interest in model evaluation, interpretability, or theoretical grounding of LLM capabilities. - Familiarity with LLMs or large-scale model training dynamics. Preferred Qualifications: - Experience with designing or analyzing model benchmarks, probing tools, or failure modes. - Exposure to AGI-related concepts, open-ended evaluation, or long-horizon generalization. - Research publications in top-tier venues such as NeurIPS, ICLR, ICML, ACL, EMNLP