Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Senior Security Researcher, Voice Agent Red Team role.
Rezi rewrites your resume against Hamming AI's job description. Free.
Tailor your resume to this Senior Security Researcher, Voice Agent Red Team role.
Rezi rewrites your resume against Hamming AI's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Senior Security Researcher, Voice Agent Red Team posting at Hamming AI — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Senior Security Researcher, Voice Agent Red Team posting at Hamming AI — free, in seconds.
About the Role
Hamming is the security layer for voice and chat agents, protecting enterprises by identifying and fixing vulnerabilities before malicious actors can exploit them. This role involves conducting authorized assessments of production systems, analyzing results, and ensuring fixes are effective.
Responsibilities
- Own the assessment, including threat modeling, scoping, testing identities, defining stopping conditions, and gathering evidence for findings.
- Follow the entire assessment path, from conversation and retrieved content to identity checks and tool permissions, identifying when an agent crosses a line.
- Work carefully in production environments with approved scenarios, controlled data, and customer consent, stopping at agreed limits.
- Prove exploitability by detailing preconditions, reproduction steps, impact, and honestly stating the severity of findings.
- Verify remediation by converting cases into regression coverage and manually teaching the harness about discovered vulnerabilities.
Requirements
- 5+ years in offensive security, including authorized assessments of production applications, APIs, or agent systems.
- Hands-on AI attack experience, such as prompt injection, jailbreak chains, tool and function-call abuse, and data exfiltration through model outputs.
- Strong understanding of application security fundamentals, including authentication and authorization bypass, injection, and session and identity handling.
- Ability to produce reports that are reproducible by developers and defensible by CISOs.
- Proficiency in Python or TypeScript for repeatable work.
Skills
- Offensive security
- Authorized assessments
- Production application security
- API security
- Agent systems security
- AI attack techniques
- Prompt injection
- Jailbreak chains
- Tool abuse
- Function-call abuse
- Data exfiltration
- Application security fundamentals
- Authentication bypass
- Authorization bypass
- Injection attacks
- Session handling
- Identity handling
- Python
- TypeScript
- Threat modeling
- Scoping
- Reporting
- Regression testing
Location
- San Francisco
- Austin
- Remote in the United States
Work Type
- Full-time
- Remote
- Onsite
Experience Level
- 5+ years
Benefits
- Competitive salary
- Meaningful equity
- Health coverage
- Dental coverage
- Vision coverage
- Access to frontier AI tools
- Sponsorship for conferences and events
- Flexible PTO
About the Company
- Hamming is the security layer for voice and chat agents.
- Banks, health systems, and other enterprises use agents on phone lines for identity verification, account access, and actions.
- Hamming proactively attacks these agents with owner permission to identify and fix vulnerabilities.
- The company boasts one of the fastest engineering teams, deploying 4 times per day.
- Ranked #1 Engineering team.
- Contributed to the OpenAI Dev Day 100 billion token list.