Red Team Lead (Offensive Cybersecurity)

SaidGig; New York (NY); Remote; USD 69,000 - 124,000; Full time

Job summary

SaidGig is seeking a Red Team Lead to shape offensive-security frameworks for AI systems. You will translate real-world cybersecurity knowledge into task taxonomies, evaluation scenarios, and clear feedback that helps AI systems reason about security.

This remote contract engagement focuses on ethical hacking, exploit chains, malware reverse engineering, and cloud/app security. The role requires 5+ years in offensive cybersecurity; senior experts with 8–20 years are preferred.

Qualifications

• 5+ years of hands-on offensive cybersecurity experience.
• Senior contributors with 8–20 years preferred.
• Experience as a principal security engineer or similar roles.
• Strong communication skills for varied audiences.
• Advanced degree or certifications valued.

Responsibilities

• Develop comprehensive taxonomies for cyber-capability tasks and attack stages.
• Design and validate offensive-security evaluation frameworks using realistic scenarios.
• Create safe proxy tasks modeling advanced attack vectors.
• Develop scoring rubrics evaluating attack sophistication, coverage, and impact.
• Review and improve red-team benchmarks to reflect evolving risks.
• Produce methodologies and technical documentation for technical and non-technical audiences.
• Collaborate asynchronously with project stakeholders and incorporate feedback.

Skills

Red Teaming

Exploit Development

Malware Analysis

Reverse Engineering

Cybersecurity Benchmarking

Technical Writing

Education

Advanced degree or security certifications

Job description

Shape next-generation AI systems with practical offensive-security expertise. As a Red Team Lead, you will turn real-world cybersecurity knowledge into high-quality task frameworks, evaluations, and feedback that improve how AI systems reason about security scenarios. Prior AI experience is not required.

Key Responsibilities

• Develop comprehensive taxonomies for cyber-capability tasks and attack stages relevant to current threat landscapes.
• Design and validate offensive-security evaluation frameworks using realistic scenarios involving exploit chains, malware, cloud and application security, and social engineering.
• Create safe proxy tasks that model advanced attack vectors while maintaining strict ethical and security boundaries.
• Develop scoring rubrics that evaluate attack sophistication, coverage, and impact across domains.
• Review and improve red-team benchmarks to reflect evolving security risks and leading practices.
• Produce clear methodologies and technical documentation for technical and non-technical audiences.
• Collaborate asynchronously with project stakeholders, incorporating feedback into deliverables.

Qualifications

• At least 5 years of hands-on experience in offensive cybersecurity, red teaming, exploit development, or vulnerability research. Senior contributors with 8 to 20 years of experience are preferred.
• Experience as a principal security engineer, exploit developer, cloud red-team lead, malware reverse engineer, or security researcher focused on attack chains or social engineering.
• Deep knowledge of cyberattack methodologies, exploit chains, and cloud or application-security assessments.
• Strong background in malware analysis, reverse engineering, social-engineering tactics, or related defenses.
• Ability to communicate actionable technical concepts clearly in writing and verbally for varied audiences.
• An advanced degree, relevant security certifications, or equivalent operational experience is highly valued.
• Experience building cybersecurity benchmarking or evaluation frameworks is a plus.

Work Terms

Remote contract engagement. Work focuses on a critical cybersecurity project and training AI systems through domain-expert input.

Compensation

$50 to $90 per hour.