Posted 5 days ago
Description
Anthropic is seeking a Research Engineer on Alignment Science to design and run thoughtful machine learning experiments that help us understand and steer high‑risk AI behavior. You’ll operate as both a scientist and an engineer, contributing to exploratory research in alignment with safety goals.
You will collaborate with teams across Interpretability, Fine-Tuning, and the Frontier Red Team, and participate in projects that advance Responsible Scaling and model safety.
#J-18808-Ljbffr
