Description
RealmLabs is seeking a highly skilled individual contributor to join their team as a Machine Learning Engineer specializing in Trust and Safety for Large Language Models (LLMs) and Multimodal LLMs (MM-LLMs). The role involves designing and conducting research experiments, publishing findings, and developing end-to-end systems to address critical security challenges such as prompt injection attacks, adversarial robustness, safety alignment, privacy, and interpretability. This foundational role contributes directly to core product capabilities within a fast-paced, early-stage startup environment.
