About this role
About Anthropic
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
About the role
The Security Risk team is responsible for how Anthropic identifies, prioritizes, and drives treatment of its most important security risks. We are rebuilding risk management to operate as an engineering function, using automation, quantitative risk and AI-native platforms to enable decision making. The risks we assess span Anthropic's full security landscape, so the team needs breadth across domains and the judgment to go deep wherever a decision demands it. Security Risk, in deep partnership with Security Engineering, helps define the security program and shapes how investment and treatment decisions get made.
The conventional GRC playbook was not built for a company shipping frontier AI. You will help define what replaces it, with a direct line to CISO-level decisions. As a Security Risk Analyst you will take risk questions from leadership and partner teams and drive them to a decision. Sometimes that is a fast, structured qualitative assessment and other times it is a deep FAIR-based quantitative analysis. Either way you bring leadership a clear position, the tradeoffs, and honest uncertainty, and you defend it under challenge. In parallel, you will help turn quantitative risk into a product partner teams can leverage, and define the standards a growing risk function will run on.
Key responsibilities
• Enable leadership and partner teams to make risk-informed decisions. Take ambiguous risk questions, drive them to a documented decision, and communicate the quantitative and qualitative tradeoffs clearly
• Lead quantitative analysis of the company's top security risk scenarios using FAIR, calibrated estimation, and simulation, working with the engineers who own the systems and presenting results in terms leadership can act on
• Partner with Security Engineering to assess threat scenarios and control effectiveness so security investment is right-sized to actual risk and remediation is sequenced where it buys down the most risk
• Frame escalations and risk treatment decisions with a clear recommendation, an honest statement of uncertainty, and re-evaluation triggers, and pressure test those decisions with risk owners
• Shape the analysis and narrative behind leadership risk reviews, and help define risk appetite and the risk metrics the organization should measure and why
• Use AI and automation to scale risk analysis, and own the calibration and quality review that keep the outputs trustworthy
• Turn one-off analyses into reusable methods, templates, and training so risk analysis becomes increasingly self service for partner teams, and raise the analytical quality of the risk re