Senior AI/ML Auditor for Frontier LLMs (Remote)

prolificacademic ltd seeks a senior AI/ML engineer to evaluate frontier LLMs, audit training code, and critique model outputs. You will focus on deep technical judgment and error tracing rather than building models, working remotely with flexible hours in the US. You will analyze prompts, assist in RLHF workflows, and benchmark reasoning quality using defined metrics and taxonomies. A strong ML background is required.