Tech Stack

Description

You will build systems to detect and mitigate misuse of AI systems, including developing classifiers for harmful behavior, monitoring multi-exchange attacks, improving agentic product safety, and conducting research on red-teaming and adversarial robustness.

Requirements

• 4+ years experience in ML engineering, research engineering, or applied research
• Proficiency in Python and experience building ML systems
• Comfortable working across research-to-deployment pipeline
• Strong communication skills to explain complex technical concepts to non-technical stakeholders
• Bachelor's degree in relevant field or equivalent

Responsibilities

• Develop classifiers to detect misuse and anomalous behavior at scale, including synthetic data pipelines and representative evaluations
• Build systems to monitor harms spanning multiple exchanges (e.g., coordinated cyber attacks, influence operations)
• Evaluate and improve safety of agentic products, including threat models and mitigations for prompt injection
• Conduct research on automated red-teaming and adversarial robustness