דרושים » AI » GenAI Tools Researcher

As a GenAI Security Researcher, youll dive deep into the challenges of AI safety, conducting redteaming operations to identify vulnerabilities in generative AI systems and their infrastructure.You will conduct redteaming operations for finding and addressing risks to ensure AI models are robust, secure, and future-proof.

As a Security Researcher, you will:
Conduct sophisticated black-box redteaming operations to uncover vulnerabilities in generative AI models and infrastructure.
Design new techniques to bypass the latest AI security mechanisms.
Evaluate and strengthen the security of AI systems, identifying weaknesses and collaborating to implement improvements.
Work with cross-functional teams to automate security testing processes and establish best practices.
Stay ahead of emerging trends in AI security, ethical hacking, and cyber threats to ensure were at the cutting edge.

We are seeking a highly motivated and experienced LLM/ML Agentic AI Researcher to lead the technical development of our agentic AI interpretation framework. This hands-on role involves designing, building, and optimizing AI agents that interpret complex biological data and generate coherent, insightful narratives explaining therapeutic mechanisms.

You will be at the forefront of developing a sophisticated scientific reasoning system that leverages Large Language Models (LLMs) to provide structured, biologically-grounded explanations. Collaborating closely with immunologists, machine learning researchers, and technical leadership, you'll shape how we derive insights at a systems level, pushing the boundaries of AI in biology.

Location: Ramat Gan, Israel (hybrid model)

What will you do?

Architect & Develop: Design, implement, and iterate on core AI agents using LLMs and Chain-of-Thought reasoning for creating a scientific reasoning system.
Integrate Biological Knowledge: Effectively access and incorporate biological databases (internal and external databases as tools) ensuring model interpretations are rooted in real biological mechanisms.
Solve Complex NLP Challenges: Innovate solutions to synthesize multiple information sources into cohesive, scientifically robust narratives. Structure advanced prompts and refine LLM interactions to achieve narrative coherence and clarity.
Robustness & Testing: Produce clean, well-documented, maintainable Python code with clear testing protocols, ensuring reliability and accuracy of the agent outputs.
Stay Ahead of Trends: Continuously explore emerging LLM technologies, APIs, and best practices to enhance our interpretation framework.
Effective Collaboration & Communication: Clearly articulate technical concepts to both technical and non-technical stakeholders, effectively integrate feedback from immunologists and researchers, and iterate rapidly to refine the interpretation framework.