AI Red Team SME - Offensive Security & AI Safety

Gracemark

Southlake (TX)

Hybrid

USD 90,000 - 96,000

Full time

3 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

401(k)
Dental insurance
Health insurance
Vision insurance

Job summary

Gracemark is hiring a Cybersecurity SME to strengthen AI safety through hands-on offensive evaluation in a hybrid role based in Southlake, TX. You will probe AI coding agents and frontier LLMs in sandboxed environments to assess cyber risk and ensure safe AI outputs.

The role requires 2+ years of offensive security experience, experience with exploit development and malware analysis, and strong Python scripting.

Qualifications

  • 2+ years hands-on offensive security experience including penetration testing, red teaming, vulnerability research, or exploit deployment.
  • Direct experience with exploit development, malware behavior, post-exploitation techniques, and web or cloud attacks.
  • Strong scripting skills (Python) to read, debug, and safely verify AI-generated code in sandboxed environments.
  • Working knowledge of LLMs, AI coding agents, and attack vectors like jailbreaks, prompt injection, and tool misuse.
  • Clear written communication to document steps and explain risks to researchers, engineers, and executives.

Responsibilities

  • Iteratively probe AI coding agents and frontier LLMs in sandboxed environments to identify functional offensive tooling, exploits, and malware.
  • Assess model outputs against safety specs, gauge violation severity, and refine evaluation criteria for unsafe capabilities.
  • Evaluate vulnerability discovery, exploit development and malware analysis, ensuring AI-generated tools execute as intended in sandboxes.
  • Investigate prompt injection, tool misuse, and privilege escalation as assessments scale to more complex agent harnesses.
  • Build realistic attack scenarios and evaluation datasets, review prompts and outputs for technical accuracy.
  • Document reproduction steps, severity ratings and mitigations; map findings to MITRE ATLAS, OWASP Top 10 for LLM Applications, and NIST AI RMF.
  • Train red teamers and annotators on offensive security concepts and emerging AI attack techniques.

Skills

Offensive security
Exploit development
Malware behavior
Python scripting
LLMs
AI agents
Red teaming
Technical reporting

Tools

Python
AWS
GCP
Azure

Job description

Gracemark is hiring a Cybersecurity SME to strengthen AI safety through hands-on offensive evaluation in a hybrid role based in Southlake, TX. You will probe AI coding agents and frontier LLMs in sandboxed environments to assess cyber risk and ensure safe AI outputs.

The role requires 2+ years of offensive security experience, experience with exploit development and malware analysis, and strong Python scripting.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Cybersecurity SME, AI Red Team
Cybersecurity SME, AI Red Team

Gracemark • Southlake (TX)

Hybrid
USD 90,000 - 96,000
401(k)
Dental insurance
Health insurance
+1
AI Red Team Engineer — Offensive Security & AI Risk Testing
AI Red Team Engineer — Offensive Security & AI Risk Testing

GraceMark Solutions • United States

On-site
USD 120,000 - 180,000
Cybersecurity SME AI Red Team
Cybersecurity SME AI Red Team

JSM Consulting India • United States

Remote
USD 90,000 - 96,000
Cybersecurity SME, AI Red Team
Cybersecurity SME, AI Red Team

GraceMark Solutions • United States

On-site
USD 120,000 - 180,000
Remote AI Red Team Cybersecurity Specialist
Remote AI Red Team Cybersecurity Specialist

Hireart • United States

Hybrid
USD 80,000 - 113,000
PTO 96 hours per year
13 paid holidays
Pre-tax commuter benefits
+4
Offensive Security Engineer for AI Safety Red Team
Offensive Security Engineer for AI Safety Red Team

Anthropic Limited • United States

Hybrid
USD 300,000 - 320,000
AI Red Teamer: Offensive Security for AI Systems (Remote)
AI Red Teamer: Offensive Security for AI Systems (Remote)

Handshake • United States

Remote
USD 150,000 - 210,000
Cybersecurity SME, AI Red Team
Cybersecurity SME, AI Red Team

Hireart • United States

Hybrid
USD 80,000 - 113,000
PTO 96 hours per year
13 paid holidays
Pre-tax commuter benefits
+4
Remote AI Red Team Cybersecurity Expert
Remote AI Red Team Cybersecurity Expert

JSM Consulting India • United States

Remote
USD 90,000 - 96,000
AI Safety Red Team Specialist - Entry Level
AI Safety Red Team Specialist - Entry Level

Hireart • Dallas (TX)

On-site
USD 34,000 - 48,000
Pre-tax commuter benefits
Healthcare benefits subsidized by Hire
Flexible Spending Account (FSA)
+2