Senior Security Researcher, Voice Agent Red Team

Hamming AI • Austin, TX

4d

About The Position

The Senior Security Researcher runs authorized assessments of production voice and chat agents at banks, health systems, and other enterprises. The role scopes engagements with the system owner, uses a testing harness to make thousands of calls, determines which results constitute consequential security failures, and writes actionable findings for the owner to fix. The researcher reruns attacks to verify remediation and turns findings into permanent regression tests. Shareable work may be published through responsible disclosure or presented on stage.

The role involves threat modeling and defining assessment scope, test identities, stopping conditions, and evidence requirements. It follows the agent's conversation, retrieved content, identity checks, and tool permissions to identify security boundary crossings. Assessments are performed carefully in production using approved scenarios, controlled data, customer awareness, and agreed limits. Findings must establish exploitability, preconditions, reproducibility, impact, remediation, and an honest severity assessment.

Requirements

• At least 5 years of offensive security experience, including authorized assessments of production applications, APIs, or agent systems.
• Hands-on AI attack experience, including prompt injection, jailbreak chains, tool and function-call abuse, and data exfiltration through model outputs.
• Application security fundamentals, including authentication and authorization bypass, injection, and session and identity handling.
• Ability to write reports that developers can reproduce and CISOs can defend.
• Python or TypeScript skills to make security work repeatable.

Nice To Haves

• Assessments of voice or telephony systems.
• Engagements with banks or health systems.
• Published research, a CVE, or a conference talk.

Responsibilities

• Own assessments by threat modeling and defining scope, test identities, stopping conditions, and evidence requirements.
• Follow the agent's conversation, retrieved content, identity checks, and tool permissions to identify security failures.
• Conduct production testing using approved scenarios, controlled data, customer awareness, and agreed limits.
• Prove exploitability by documenting preconditions, reproduction steps, impact, remediation, and severity.
• Verify remediation by turning cases into regression coverage and teaching the testing harness from manual findings.
• Share appropriate work through responsible disclosure and presentations.

Benefits

• Competitive salary and meaningful equity.
• Health, dental, and vision coverage.
• Every frontier AI tool fully paid from day one.
• Conferences and events sponsored by the company.
• Flexible PTO.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed