ML/Research Engineer, Safeguards

Overview

Build and deploy safeguards systems to detect and mitigate harmful or policy-violating misuse of AI, including coordinated attacks, and help models behave appropriately across contexts.

What you'll do

• Develop classifiers to detect misuse and anomalous behavior at scale.
• Create synthetic data pipelines and representative evaluation sourcing methods to iterate on training.
• Monitor for multi-exchange harms such as coordinated cyber attacks and influence operations.
• Evaluate and improve safety of agentic products by building threat models/environments and deploying mitigations for prompt injection attacks.
• Conduct research on automated red-teaming and adversarial robustness to uncover misuse.

What you'll need

• 4+ years of experience in ML engineering, research engineering, or applied research.
• Proficiency in Python and experience building ML systems.
• Comfort working across the research-to-deployment pipeline.
• Concern about misuse risks of AI systems and a desire to mitigate them.
• Strong communication skills to explain complex technical concepts to non-technical stakeholders.

Details

• Annual compensation range: $350,000–$500,000 USD.
• Location policy: expect staff to be in an office at least 25% of the time.
• Visa sponsorship is available, but not guaranteed for every role/candidate.
• Minimum education: Bachelor’s degree (or equivalent combination of education/training/experience).
• Required field of study: field relevant to the role as demonstrated through coursework, training, or professional experience.