[Hiring] Senior AI Researcher @Zenity

Role Description

This is a research‑first role focused on deeply understanding LLM internals to improve the security of AI agents. You’ll design careful experiments on activations and interpretable features 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 You’ll Do

• Investigate model internals, including activation/features analysis, unsupervised clustering, discovery of directions in latent space.
• 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 Zenity Labs posts and open artifacts; aim for tier‑1 ML venues (NeurIPS, ICML, etc.) and security forums.
• Build tools: adapt existing open source libraries and create agents to automate research work and distill knowledge from designed experiments.

Requirements

• Deep learning expertise with a track record of non‑trivial research (industry or academia) in LLMs or other domains (e.g., CV, speech).
• Strong experimental design and scientific writing; comfort pre‑registering hypotheses, testing causal claims, proposing novel directions in a fast-changing field.
• PhD or equivalent research experience in the industry (5+ years in a leading research team).
• Publication record or a portfolio of high‑impact open artifacts will make you stand out from the crowd.
• Familiarity with AI frameworks (e.g., HuggingFace Transformers, LangChain, scikit-learn, PyTorch); experience with a production grade codebase with several contributors is a bonus.
• Experience in data analysis: visualization, exploration, cleanup.
• Knowledge in GenAI tools such as LLM Orchestrations and integration packages, Agents, RAG systems - a bonus.