Senior Engineer, Offensive Security (AI)

TL;DR

Senior Engineer, Offensive Security (AI): Building production-grade AI agents and offensive security tooling for penetration tests, purple-team exercises, red-team operations, and adversarial testing of internal AI systems with an accent on agentic workflows, cloud platforms, and LLM security. Focus on designing event-driven tooling, testing prompt injection and model abuse, and translating live engagement findings into reliable security capabilities.

Location: Remote nationwide within the United States; occasional travel to hirify.global offices for training or meetings may be required. A dedicated, interruption-free workspace and internet service with at least 25 Mbps download and 10 Mbps upload are required.

Salary: $117,600–$161,700 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

• Build and operate production-grade Python tooling, AI agents, LLM planning loops, function-calling capabilities, and multi-agent orchestration.
• Develop and operate an event-driven cloud platform supporting offensive security workflows at scale.
• Conduct network, web application, cloud, and infrastructure penetration tests from reconnaissance through exploitation and lateral movement.
• Run purple-team exercises with defensive partners to validate EDR/XDR, NDR, DLP, firewall, and detection controls.
• Lead objective-driven red-team operations and adversarial assessments of LLM products, agents, RAG pipelines, and ML applications.
• Deliver reproducible findings, severity assessments, business impact, remediation guidance, and measurable tooling improvements.

Requirements

• 4+ years of offensive security experience in red teaming, penetration testing, purple teaming, control validation, or bug bounty work.
• Production Python engineering experience, including building and operating real tooling.
• Hands-on experience designing, building, or operating AI agents and LLM applications with agentic workflows, function calling, or orchestration.
• Hands-on experience testing AI/ML systems, including prompt injection, jailbreaking, and adversarial techniques.
• Production experience with at least one major cloud provider: AWS, GCP, or Azure.
• Must be able to work remotely within the United States and protect PHI/HIPAA information in a dedicated workspace.

Nice to have

• Experience with autonomous offensive agents, LLM-driven penetration-testing agents, or reinforcement-learning attack planners.
• Knowledge of C2 frameworks, evasion, OPSEC, EDR/XDR, MITRE ATT&CK, VECTR, or Atomic Red Team.
• Experience with PyRIT, Garak, MITRE ATLAS, OWASP Top 10 for LLM Applications, NIST AI Risk Management Framework, MCP, or RAG security.
• Advanced offensive security, cloud penetration testing, threat intelligence, adversarial ML research, published research, or relevant conference contributions.
• Offensive or AI-security certifications such as OSCP, OSEP, OSCE3, CRTO, CPTS, CWES, or OSAI.

Culture & Benefits

• Considerable autonomy on moderately complex engagements and influence over technical direction.
• Dedicated Fridays for research and development.
• Access to Hack The Box Pro Labs, role-based paths, certifications, conference budgets, and training funding.
• Medical, dental, vision, 401(k), paid time off, holidays, parental and caregiver leave, disability coverage, and life insurance.
• Work combines software engineering, live offensive operations, collaborative detection validation, and responsible use of AI.