A

Senior Red-Team Engineer, AI Agent Security

Visa Sponsorship Relocation
Apply
AI Summary

Lead the red-teaming and certification of frontier AI agents for enterprise clients, ensuring security and reliability standards. Refine core evaluation engines, productize adversarial attacks, and manage end-to-end technical scoping and remediation. Requires strong backend engineering skills, AI-native workflow expertise, and the ability to communicate technical trade-offs to CISOs.

Key Highlights
Lead end-to-end red-teaming of the world's most used AI agents from scoping to certification.
Refine the core engine running all red-teaming evaluations and productize frontier adversarial attacks.
Work directly with customers' agents and translate technical trade-offs to CISOs.
Key Responsibilities
Lead the red-teaming of the world's most used AI agents, working directly with customers' agents end-to-end from scoping to certification.
Refine the core engine that runs all red-teaming evals.
Act as DRI end-to-end for technical scoping, reconnaissance, execution, remediation, and certification.
Productize frontier adversarial attacks.
Taste-test the evals to set the quality bar.
Productize your workflow with agents.
Figure out how to eval new types of agents, e.g. computer use.
Technical Skills Required
Backend Engineering AI Agent Security Red-Teaming
Benefits & Perks
Equity compensation
Competitive benefits
Visa sponsorship
Relocation stipend

Job Description


About AIUC

Our mission is to underwrite superintelligence. We red-team, certify, and insure agents - working with AI category leaders like ElevenLabs, Lovable, Harvey, UiPath, and Fin.

Soon, agents will take on critical work in hospitals, banks and governments. This could create abundance - or go terribly wrong. History teaches us that standards and insurance are capitalism’s best tools for making risk legible and shaping incentives.

We’ve built the gold standard for agent security & reliability, AIUC-1, with 100+ CISOs from the Fortune 1000. Our team comes from Anthropic, McKinsey, METR, Palantir, Amazon - 50% are previous founders. We've raised $55m from Ribbit, First Harmonic, and Nat Friedman. Read more here, here, and here.

The role

You’ll lead the red-teaming of the world’s most used AI agents, working directly with our customers' agents end-to-end from scoping to certification.

  • Refine the core engine that runs all our red-teaming evals
  • DRI end-to-end: technical scoping, reconnaissance, execution, remediation, certification
  • Productize frontier adversarial attacks
  • Taste-test the evals to set the quality bar
  • Productize your workflow with agents
  • Figure out how we eval new types of agents, e.g. computer use

What We're Looking For

You thrive across tinkering with complex AI workflows and translating technical trade-off to CISOs.

  • Entrepreneurial drive to get-things-done fast
  • AI native in how you work
  • Experience writing backend production grade code real users depend on
  • Strong computer science or engineering foundation
  • Crisp communicator on technical topics
  • Thrives with working hard in fast-paced environments

Compensation & Perks

  • Equity is a significant part of total compensation, in addition to salary
  • Competitive benefits
  • Visa sponsorship and relocation stipend to bring you to SF, if possible

Our values

Strong Back - High standards, keep our promises, work hard

Fast Feet - Experiment, cut scope, take delight in pace

Eyes Up - ‘Feel the AGI’ across our strategy, teams and day-to-day work

Open Heart - Say the scary thing, create connection, make room for emotions

Similar Jobs

Explore other opportunities that match your interests

Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Not Applicable

forerunner

United State

Founding Full-Stack Engineer

Programming
10h ago
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Mid-Senior level

anyura

United State
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Entry level

torentify

United State

Subscribe our newsletter

New Things Will Always Update Regularly