Week 2024-W16
2 new AI roles opened across 1 companies. Highest-signal roles first.
Anthropic· 2 roles
- Research Scientist, Interpretability Post-train · Research 10Research Scientist focused on mechanistic interpretability of LLMs, aiming to understand how neural network parameters map to algorithms for safety and steerability. Involves developing methods, running experiments, building infrastructure, and communicating results.
- Research Manager, Interpretability Post-train · Research 10Manager for the Interpretability team focused on mechanistic interpretability of large language models, aiming to understand how they work internally for AI safety.