Toloka AI / careers
← All positions

AI safety evaluation · Toloka AI

Red Teaming Fellowship

United StatesNot specifiedNot specified

Role Summary

Test AI models and agents under adversarial and unexpected conditions. Help identify failure modes and improve methods for evaluating safety, security, and reliability.

This published opportunity is available through Toloka AI. Review the listing carefully for the specific work arrangement and requirements.

Responsibilities

Run safety and misuse testing scenarios. Develop prompts, test cases, and attack strategies. Analyze behavior and write actionable findings. Improve evaluation frameworks and taxonomies. Research emerging threats and create visualizations.

Qualifications

Relevant degree in progress or recently completed; familiarity with AI abuse; analytical, research, and communication skills; ability to work independently and collaboratively.

Preferred Qualifications

Python/Bash, LLM or cybersecurity experience, research methods, and proficiency beyond English.

Benefits

Not disclosed

What happens next

Submit your interest online to receive a reference number. The opportunity owner or review team may contact selected applicants about next steps.

For accommodation requests, contact [email protected].