דרושים » AI » Sr Staff Researcher, AI Security

As our Senior Staff Product Security AI Lead Researcher, you will spearhead research and development efforts focused on advanced guardrails for securing our Generative AI (GenAI) and agentic AI systems. You will lead AI and data science initiatives to pioneer methods for assessing and improving the security and safety of our AI models. Collaborating closely with the engineering team, specialised security researchers, and other AI specialists, you will translate cutting-edge research into actionable security solutions that significantly enhance the integrity of our AI offerings.

What Youll Do:
Lead innovative AI security and safety research, particularly around developing and refining guardrails for GenAI and agentic AI.
Design, implement, and oversee comprehensive testing protocols and evaluations to ensure AI model security and robustness.
Work collaboratively with engineering teams and specialized security researchers to integrate security best practices into the AI development lifecycle.
Provide expert insights on emerging threats and vulnerabilities unique to AI systems and propose effective mitigation strategies.
Communicate research outcomes clearly, influencing technical and strategic decisions throughout the organization.
Actively contribute to thought leadership in the AI security domain, participating in internal and external presentations, research publications, and standards development.

The Content Safety Team, which is responsible for ensuring a safe environment for our customers, is seeking a Senior AI Scientist. The team develops content moderation solutions for user-generated and AI-generated content across all products and utilizes advanced GenAI tools to build capabilities such as automatic labeling.
We encourage you to apply if you
Are passionate about using advanced ML techniques and evolving technology to create a safe environment for customers
Love working as part of a team of experienced AI scientists that love research and innovation just as much as they love getting models to production and making an impact
Are interested in partnering with analysts and researchers to implement your ideas into mitigation policies that keep the bad actors away
Take pride in having end to end ownership of your models - from conception, throughout research and development to production and monitoring
Responsibilities
Develop and refine content moderation models to filter and tackle abusive content across various products, content types and modalities.
Work extensively with NLP algorithms, focusing on fine-tuning transformers and large language models (LLMs) to enhance accuracy and efficiency.
Explore and integrate advanced technologies such as Retriever-Augmented Generation (RAG) and Agentic AI to assist in the automatic labeling and classification of data.
Collaborate with a multi-disciplinary team including machine learning engineers, AI scientists, and policy experts to ensure models align with ethical standards and company policies.
Stay updated with the latest research in AI and machine learning to incorporate cutting-edge techniques into content moderation strategies.
Prepare and maintain documentation on model development, configurations, and performance metrics for both technical and non-technical audiences.
Mentor and guide junior AI scientists, fostering a collaborative and productive team environment.