[Remote] Student Researcher [Seed Vision – Multimodal Interaction & World Model Pretraining] – 2026 Start (PhD)

Note: The job is a remote job and is open to candidates in USA. ByteDance is dedicated to pioneering advanced AI foundation models and is seeking a PhD intern for their Seed Multimodal Interaction and World Model team. The role involves contributing to research and engineering efforts to enhance multimodal understanding and developing models for interactive exploration. Responsibilities Contribute to research and engineering to advance world models and multimodal understanding, enhancing models' reasoning and generation capabilities Design and prototype novel architectures that balance modeling performance, generalization, and efficiency Help establish scaling laws and conduct systematic ablations to derive transferrable insights across model families and tasks Skills Currently pursuing a PhD in Computer Vision, Machine Learning, or a related technical field Familiarity with multimodal modeling, world models, or foundation model pretraining Strong coding skills and hands-on experience with PyTorch or JAX Experience with large-scale distributed training frameworks and GPU/TPU compute stacks Demonstrated research ability, with publications in top-tier conferences such as CVPR, ICCV, ECCV, NeurIPS, ICML, or ICLR Experience working with transformer-based architectures, including dense and Mixture-of-Experts (MoE) models Understanding of scaling behavior in foundation models and how to analyze them Familiarity with data preparation pipelines for large-scale multimodal pretraining Benefits Interns have day one access to health insurance Life insurance Wellbeing benefits and more Interns also receive 10 paid holidays per year Paid sick time (56 hours if hired in first half of year, 40 if hired in second half of year) Interns who are not working 100% remote may also be eligible for housing allowance. Company Overview ByteDance is a technology company that develops content creation platforms and services. It was founded in 2012, and is headquartered in Beijing, Beijing, CHN, with a workforce of 10001+ employees. Its website is Company H1B Sponsorship ByteDance has a track record of offering H1B sponsorships, with 1350 in 2025, 1123 in 2024, 775 in 2023, 487 in 2022, 417 in 2021, 245 in 2020. Please note that this does not guarantee sponsorship for this specific role.