Toloka AI / careers
← All positions

AI safety evaluation · Toloka AI

Enforcement Analyst, Agentic Alignment

United StatesHybridNot specified

Role Summary

Investigate harmful or unexpected autonomous-model behavior and assess real-world risk. Make defensible enforcement decisions and feed findings into safeguards and model improvements. Available cities include Boston, San Francisco, Seattle, New York City, and Washington.

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

Responsibilities

Review transcripts, tool traces, and code for misalignment. Triage cases by severity and urgency. Assess harmful cyber-related agent activity. Document evidence, reasoning, and enforcement decisions. Identify patterns and improve review workflows.

Qualifications

Code-reading ability; security or threat-intelligence background; structured investigations and enforcement experience; clear writing; escalation judgment and resilience around disturbing content; relevant bachelor's degree or equivalent background.

Preferred Qualifications

AI-assisted investigation, large-dataset analysis, and AI safety/alignment familiarity.

Benefits

Vacation and parental leave; optional equity donation matching.

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].