FAR.AI Benefits Overview

Lead an AI safety research agenda focused on reducing catastrophic risks from advanced AI. Responsibilities include setting research direction, building and mentoring technical teams, conducting hands-on experiments, communicating findings, securing grants, convening researchers, and connecting research to AI company and government adoption.

Leads engineering for FAR.AI’s frontier AI red-teaming program, building scalable tools, evaluation systems, agentic workflows, vulnerability databases, and reporting infrastructure. Manages and grows an engineering team, sets execution priorities, mentors staff, hires leaders, and partners with AI companies and governments on high-stakes testing. The role translates technical strategy into systems and processes that identify vulnerabilities, strengthen safeguards, and advance AI security standards.

Conduct applied AI safety research using white-box methods such as activation explainers, steering, attribution, and model-internal interventions. Evaluate methods on realistic, large-scale models and agentic coding tasks, develop practical monitors and interventions, publish findings, propose research directions, and engage with researchers, frontier AI developers, governments, and the broader AI alignment community.