AI Red Team – GenAI Adversarial Evaluation
Description
We are looking for a scientist/analyst to evaluate AI models at Alice, a company specializing in safety and security of artificial intelligence systems. In this role, you will test and validate various attack scenarios such as prompt injection, data theft, and tool misuse to ensure they are realistic, fair, and reproducible with precision. You will combine security expertise with statistical analysis and LLM-based tools to identify quality issues, learn from attack patterns, and recommend improvements. Required: 4+ years of experience in research or analytics, proficiency in Python and statistics, and deep knowledge of attacks on LLM systems and AI-based applications. Location: Ramat Gan · Remote work · Full-time · Department: Security To apply: On the company website, via the button below
Details
Company
Alice
Location
Remote
Location
Ramat Gan
AI Red Team – GenAI Adversarial Evaluation
This role is published on Alice's own site. You apply there; our part is getting it seen.
All open roles at Alice →Apply on the company siteWant up to 3 matching jobs by mail every morning? Paste your CV.Ask about this listingSource
This listing was collected from a public external source. To contact the poster, visit the original post.
Original page at comeet.com