Research Scientist Intern

Six-month PhD research internship aimed at publishing novel work in decentralized model training at frontier scale. The intern owns a foundational research question blocking larger runs, with significant compute access and senior scientist mentorship, targeting tier-1 venues. Topics include communication-efficient training, fault tolerance to node churn, heterogeneous compute and networks, and robustness to malicious participants. Requires active PhD candidacy with at least one top-tier publication, deep learning and distributed systems theory, and PyTorch proficiency.