כניסההרשמה
חזרה

Senior AI Researcher

Zenity
שכר לא צויןTel Aviv, Tel Aviv-Jaffa, Israel, מהמשרדסניורמשרה מלאה
משרה חיצונית, ההגשה באתר החברהאושר שהמשרה פתוחה לפני 14 שעות

You will study LLM internals to find mechanisms behind attacks on AI agents and turn research findings into signals for detection and analysis. You will design evaluations, build research tools, and share results through publications and open artifacts.

מה תעשו

  • Investigate model internals through activation and feature analysis, clustering, and latent-space analysis.
  • Design security-focused evaluations using datasets for different attack types and compare white-box methods with black-box baselines.
  • Publish research findings and share code or trained models when relevant.
  • Build and adapt research tools, including agents to automate research and summarize experiment findings.
  • Train specific model components when needed to improve interpretability metrics.

דרישות

  • Deep learning expertise and a record of significant research in LLMs or another domain.
  • Strong experimental design and scientific writing skills.
  • PhD or equivalent industry research experience, including 5+ years in a leading research team.
  • Familiarity with AI frameworks such as HuggingFace Transformers, LangChain, scikit-learn, or PyTorch.
  • Experience in data analysis, including visualization, exploration, and cleanup.

יתרון

  • Experience with a production-grade codebase with several contributors.
  • Knowledge of LLM orchestration and integration packages, agents, or RAG systems.
  • Publications or a portfolio of high-impact open artifacts.

תנאי סף

  • PhD or equivalent industry research experience
  • 5+ years of experience in a leading research team (for equivalent industry research experience)
LLM interpretabilityDeep learningPyTorchHuggingFace TransformersExperimental designData analysis