דרושים » AI » Research Infra Engineer

This is a research‑first role focused on deeply understanding LLM internals to improve the security of AI agents. Youll design careful experiments on activations and interpretable features- e.g., probing, attribution & ablation/patching, representation‑geometry analyses-to uncover mechanisms behind jailbreak, indirect prompt injection, and other attacks. Then translate those insights into signals that can be used for detection and analysis of a model response.

The field of LLM interpretability at scale is exploding, with several major publications in the last months, and major opportunities for innovation.

What Youll Do
Responsibilities:
Investigate model internals, including activation/features analysis, unsupervised clustering, discovery of directions in latent space, etc. It may also require training specific model parts to improve interpretability metrics.
Design security‑grounded evaluations: curate datasets for different attack types, evaluate performance of different white box (model internals) methods compared to black box (input/output only) baselines.
Publish and share: produce our Labs posts and open artifacts; when the work is strong, aim for tier‑1 ML venues (NeurIPS, ICML, etc.) and security forums. A publication of code and/or trained models in cases of community relevant novelty.
Build tools: Several open source libraries exist (like Anthropics attribution graphs infra), but the research in the field is very dynamic, which will require you to build and adapt tools to your own research directions. This also includes agents to automate research work and distill knowledge from designed experiments.

We are seeking a Senior NLP/LLM Researcher to conduct advanced research and develop innovative applications focused on protecting and evaluating LLMs & agentic applications. In this role, you will collaborate with a multidisciplinary team of scientists and engineers, working together to address critical challenges. You will be responsible for designing, implementing, and evaluating new algorithms, models, and agents that help safeguard LLMs.