Opportunity Description
Overview
Drive forward our AI security initiatives as an Adversarial Machine Learning Engineer. In this hands‑on role, you'll play a vital part in fortifying LLM systems against vulnerabilities. As a key member of our AI Red Team, you will focus on adversarial testing, executing various attack simulations to expose weaknesses in AI deployments.
Key Responsibilities
- Perform adversarial testing on large language models
- Simulate attacks, including data exfiltration and jailbreaking
- Develop scripts for automated attack scenarios
- Analyze AI model resilience under pressure
- Work with teams to ensure remediation efforts are effective
Requirements
- Robust experience in adversarial machine learning
- Familiarity with AI systems and model tuning
- Advanced Python development for custom tooling
- Understanding of guardrails and safety mechanisms
- Cybersecurity experience ...
Interested in this opportunity? Apply now through Expertini.
Apply for this Position