Head of Red Teaming

Syntony’s red teaming is human-first. Our red teamers have worked for top frontier labs, social media platforms, and the U.S. government, and our Trusted Red Team Network includes top performers in Gray Swan Arena competitions, on HackerOne, and on Hack The Box. Engagements end with in-person workshops that walk clients through what we found and connect it to their governance practice.

You will own the practice as it grows: methodology, delivery, the quality of the network, and our red teaming training. You will work closely with the founder and with our Head of Research Strategy and Evaluations, and help shape the products that support red teaming at scale, including BLACKLINE and A440.

• Lead red teaming engagements from scoping and threat modeling through testing, reporting, and client workshops.
• Set and maintain Syntony’s red teaming methodology, including test design, evidence standards, severity ratings, and retesting.
• Recruit, vet, and coordinate Trusted Red Team Network members, match people to projects, and review the quality of their findings.
• Extend our testing in areas such as vulnerable user harms, insider threats, agentic systems and loss of control, and physical AI.
• Turn findings into clear reports and recommendations that clients can act on in their governance and assurance decisions.
• Help design and deliver Syntony’s red teaming training for client teams.
• Support business development through technical scoping, proposals, and conversations with prospective clients and partners.
• Set safety, confidentiality, and wellbeing practices for red teamers who work with sensitive or distressing material.

• 5+ years in red teaming, adversarial testing, offensive security, trust and safety, or a closely related field.
• Hands-on experience red teaming AI models or agents, whether at a frontier lab, a technology company, a bug bounty platform, or in public competitions.
• Experience leading testing projects or teams, including scoping work and reviewing other people’s findings.
• Sound judgment about handling and disclosing sensitive findings responsibly.
• Clear writing for technical and non-technical readers, and comfort presenting findings to senior client stakeholders.
• Comfort working through ambiguity at an early-stage company, taking ownership of open-ended problems as priorities change.

Experience with AI evaluation, governance frameworks, or threat modeling for emerging technology is useful. We assess demonstrated work and judgment; a graduate degree is not required.

This role can be part-time or full-time. Syntony is scaling, so we will shape the role around your availability and what the work needs. We will agree a weekly commitment and scope before you start and revisit them as the company grows.

The role comes with generous cash compensation and equity, which we will discuss in the initial interview. Final terms will be agreed in writing before work begins.

The position is remote.

The role also comes with a generous startup benefits package, including a monthly health and wellbeing stipend, WiFi and phone reimbursement, travel and commuter benefits, a monthly compute budget, and coworking privileges. Read more about our culture and benefits.