Lead, Offensive Security (AI & Tooling)

Location: 100% remote, but must reside within 60 minutes of Louisville, NYC Metro, Dallas Metro, Charlotte NC Metro, South Florida (Tampa/Miami/Fort Lauderdale), Washington DC Metro, Chicago, Boston, Atlanta, or Nashville. Occasional travel to hirify.global offices for training or meetings may be required.

Salary: $142,300–$195,700 per year, plus eligibility for a bonus incentive plan.

Company

hirify.global is a U.S. healthcare company providing insurance and healthcare services to millions of people.

What you will do

• Own the architecture, roadmap, and operation of an in-house AI agent platform for red team, breach and attack simulation, and penetration testing.
• Build autonomous and semi-autonomous agents for reconnaissance, exploitation, privilege escalation, lateral movement, and offensive tooling execution.
• Develop multi-agent orchestration, tool and function calling, event-driven cloud services, serverless functions, data pipelines, alarms, and LLM inference integrations.
• Red-team enterprise AI products, agents, RAG pipelines, and ML applications for prompt injection, jailbreaks, model extraction, poisoning, evasion, and tool or sandbox abuse.
• Deliver production-grade tools with reproducibility, evaluation, safety guardrails, human-in-the-loop controls, findings, remediation guidance, and risk tracking.
• Establish agent evaluation metrics, publish the offensive-AI roadmap and KPIs, and mentor 1–3 engineers.

Requirements

• 6+ years of offensive security experience in red team or penetration testing roles, including team- or program-level leadership.
• Strong production Python engineering experience building and operating software and tooling beyond scripts.
• Hands-on experience designing, building, or operating AI agents or LLM applications, including agentic workflows, tool or function calling, and orchestration.
• Hands-on testing of AI/ML systems using prompt injection, jailbreaking, and other adversarial techniques.
• Production experience with at least one major cloud provider: AWS, GCP, or Azure.
• Must meet the U.S. residence requirement and maintain a dedicated work space and wired DSL or cable internet with at least 25 Mbps download and 10 Mbps upload; satellite and wireless internet are not allowed.

Nice to have

• Experience building autonomous offensive agents, LLM-driven penetration-testing agents, or reinforcement-learning attack-path planners.
• Experience with PyRIT, Garak, MITRE ATLAS, OWASP Top 10 for LLM Applications, or the NIST AI Risk Management Framework.
• Experience with Model Context Protocol, RAG pipeline security, EDR/XDR-protected endpoints, multiple cloud providers, or threat-intelligence-driven operations.
• Advanced offensive expertise in malware development, red team operations, threat simulation, adversarial ML, or AI infrastructure.
• Published research, open-source contributions, conference talks, or expert-level offensive security certifications.

Culture & Benefits

• 100% remote work within the specified U.S. location requirement.
• Fridays dedicated to research and development in offensive security, agents, LLMs, and artificial intelligence.
• Access to Hack The Box Pro Labs, role-based training paths, certifications, discretionary certification funding, and conference or training budgets.
• Medical, dental, and vision benefits, 401(k), paid time off, holidays, paid parental and caregiver leave, disability coverage, and life insurance.
• Work focused on protecting health data and improving offensive security capabilities at production scale.