ByteDance is looking to solve the problem of discovering new approaches to general intelligence and pushing the boundaries of AI through foundational research
Requirements
- 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.
- 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.
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.
Other
- Currently pursuing a PhD in Machine Learning, Artificial Intelligence, or a related field.
- Please state your availability clearly in your resume (Start date, End date)
- Applications will be reviewed on a rolling basis – we encourage you to apply early.
