Agentic Risk Analyst

Details

The Intelligence and Investigations team identifies and mitigates abuse and strategic risks to support a safe online ecosystem. The Strategic Intelligence & Analysis team provides safety intelligence for OpenAI products by monitoring, analyzing, and forecasting real-world abuse, geopolitical risks, and strategic threats.

As an Agentic Risk Analyst, you will shape OpenAI’s operating picture for current agentic risk across products and platforms. You will connect incidents, technical findings, abuse patterns, and external developments to workstreams, mitigations, owners, dependencies, and residual gaps. The role focuses on risks arising from autonomy, multi-step task execution, tool use, memory, retrieval, connectors, computer-use capabilities, and multi-agent workflows, including adversarial misuse and unintended system behavior.

You will collaborate with investigators, engineers, product, policy, safety, security, measurement, and forecasting teams to coordinate risk decisions and follow-through across increasingly capable agentic systems.

Responsibilities

• Build and maintain a company-wide portfolio of material agentic risks across products, platforms, and emerging capabilities.
• Map risks to workstreams, owners, mitigations, dependencies, decisions, and residual gaps.
• Run cross-functional intake and review processes for emerging risks and evolving threat patterns.
• Connect incidents, technical findings, evaluations, and weak signals to system-level trends.
• Produce assessments covering impact, severity, evidence, uncertainty, priority, and recommended action.
• Assess how capability changes, product launches, ecosystem developments, and adversary adaptation affect risk priorities and launch readiness.
• Surface risks that are unowned, stalled, or under-mitigated, and track residual risk after launch.
• Use external developments in AI safety and security research, public incidents, adversarial activity, industry standards, emerging technologies, and competitor products to inform prioritization.
• Refine frameworks and taxonomies for agentic failure modes, control gaps, abuse patterns, and downstream harms.
• Produce concise, decision-ready analysis with assumptions, confidence levels, competing hypotheses, prioritized recommendations, accountable owners, and review dates.
• Define and track program metrics such as coverage, ownership, decision latency, mitigation status, and closure.
• Partner with evaluation, scenario analysis, tabletop exercise, red-team, and investigations teams to drive measurable mitigation follow-through.

Requirements

• Typically 7+ years of experience in trust and safety, integrity, security, cyber threat intelligence, AI safety, product risk, strategic intelligence, abuse investigations, or a related field.
• Strong understanding of modern AI systems and agentic architectures, including hands-on experience using, evaluating, or building agentic systems.
• Familiarity with AI safety concepts, agentic failure modes, and misalignment risks.
• Experience analyzing how harmful outcomes emerge from interactions between users, products, and technical systems, including fraud, scams, social engineering, coordinated influence operations, cyber abuse, and other platform misuse.
• Experience operating a cross-functional risk, safety, security, or integrity program and driving ownership, dependency resolution, escalation, and follow-through without direct authority.
• Exceptional analytical judgment and experience producing assessments under uncertainty.
• Strong technical fluency and ability to translate technical findings into clear risk assessments.
• Experience synthesizing investigations, telemetry, evaluations, experiments, dashboards, and external research.
• Experience with SQL, Python, and analytical tools is a plus.
• Experience applying risk frameworks, threat models, severity assessments, taxonomies, or prioritization frameworks.
• Strong written and verbal communication skills, including executive-ready analysis.
• Ability to build practical operating processes and tools in fast-moving environments.

Benefits

• Medical, dental, and vision insurance.
• Health Savings Accounts and pre-tax Flexible Spending Accounts.
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off, company holidays, office closures, and paid sick or safe time.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Equity and performance-related bonuses for eligible employees.