לוח משרות דרושים במרכז, לחיפוש זה נמצאו 31,206 משרות

we are looking for a Senior AI Engineer.
As a Senior AI Engineer on the Guardian Agents team, you will develop both our autonomous "digital employees" that execute security programs and the Control Plane that governs them. You will build a platform that allows customers to calibrate agents through conversation, ensuring human feedback is transformed into persistent organizational knowledge. By engineering these closed-loop systems, you enable agents to learn, evolve, and deliver accurate, goal-driven security outcomes at scale.
Architect Autonomous Agents: Build goal-driven agents for complex security tasks like false-positive reduction and automated triage.
Build the Control Plane: Develop the infrastructure for Human-in-the-Loop (HITL) feedback, natural language calibration, and stateful memory systems.
Engineer for Growth: Implement evaluation frameworks and "organizational memory" to ensure agents stay accurate and follow historical security precedents.
Bridge AI & Engineering: Collaborate in a "Core Pod" with Security Researchers and Data Scientists to turn raw security signals into scalable, productized agent behaviors.
Scale Data Pipelines: Integrate agents with Big Data foundation to ensure real-time context and tenant-safe execution.

we are looking for a Senior AI Researcher.
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.
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 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.