Enforcement Analyst Agentic Alignment
Posted Updated
Description
You will investigate harmful and unexpected model behavior using transcripts, tool-use traces, code, logs, and data. You will triage cases, make and document enforcement decisions, assess cyber-related activity, write evidence-based findings, and improve review workflows. You may encounter explicit sexual, violent, or psychologically disturbing content and participate in on-call responsibilities.
Responsibilities
- Review and investigate potential agentic-misalignment cases
- Triage cases by severity and urgency
- Operationalize scalable review pipelines for agentic cases
- Make and document Usage Policy enforcement decisions
- Assess cyber-related agentic activity and real-world harm potential
- Write evidence-based case reports for varied audiences
- Identify case trends and provide findings to policy, detection, and research teams
- Maintain enforcement documentation, review logic, and precedents
- Collaborate with Threat Intelligence, Research, Engineering, and Policy partners
- Use AI systems to summarize transcripts, analyze code, query data, and build lightweight tooling
- Contribute to reports on agentic harm trends and enforcement outcomes
Requirements
- Ability to read and understand Python, JavaScript, or shell scripts
- Background in security, cyber threat intelligence, or a similar technical field
- Experience in trust and safety, enforcement, investigations, or a related field
- Experience conducting structured investigations
- Experience supporting formal enforcement actions, case documentation, evidence packaging, and escalation coordination
- Clear writing and stakeholder communication
- Judgment about escalation and resilience when working with difficult content
- Bachelor’s degree or equivalent education, training, or experience
Benefits
- Optional equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours
Skills
Sign in to read and join the discussion.