AI Security Research & Red Team Engineer (AI)

TL;DR

AI Security Research & Red Team Engineer (AI): Researching AI-specific vulnerabilities and conducting adversary simulations across hirify.global’s infrastructure, corporate networks, and product ecosystems with an accent on LLMs, coding agents, prompt injection, and security efficacy. Focus on building attack scenarios, validating defensive detections, partnering with blue-team functions, and translating complex exploits into risk-based recommendations.

Location: Hybrid. New York-based hires are eligible for the stated salary range; in-person interviews may be required at a hirify.global office or hub at the offer stage. The position may require authorization to access technology controlled under U.S. export control laws without export-license sponsorship.

Salary: $166,000–$208,000 annually for New York-based hires; compensation may vary by work location. The role is also eligible for hirify.global’s equity plan.

Company

hirify.global operates a large global network that protects and accelerates Internet applications and provides security, performance, and reliability services.

What you will do

• Conduct AI security and vulnerability research across LLMs, coding agents, agentic implementations, and hirify.global products.
• Execute full-chain red-team operations against global infrastructure, corporate networks, and product ecosystems.
• Design agentic testing, breach-and-attack simulations, payload delivery frameworks, and command-and-control infrastructure.
• Measure the effectiveness of WAF, EDR, and SIEM detections against MITRE ATT&CK tactics, techniques, and procedures.
• Partner with incident response, threat detection, threat engineering, product engineering, SRE, and GRC teams to turn findings into defensive and compliance improvements.
• Mentor engineers and communicate technical exploit findings and risk priorities to executive stakeholders.

Requirements

• 4+ years of experience in offensive security, application security, or a related field.
• Deep knowledge of AI, LLMs, coding agents, prompt engineering, prompt injection, jailbreaking, and agentic concepts.
• Strong background in manual penetration testing, exploit development, or cloud security across AWS, GCP, or bare-metal environments.
• Experience using the MITRE ATT&CK framework to map defensive coverage and identify telemetry gaps.
• Ability to explain complex exploits to non-technical stakeholders and collaborate with engineering teams.
• Knowledge of automated breach-and-attack simulation tools and custom payload-delivery and C2 frameworks.

Culture & Benefits

• Work in a collaborative red-team and blue-team environment focused on curiosity, ethical hacking, and continuous improvement.
• Contribute to security initiatives that protect hirify.global and its customers across a large-scale Internet network.
• Participate in hirify.global’s equity plan.
• Support may include projects protecting journalism, civil society organizations, election websites, and public Internet services.

Hiring process

• Applicants progressing to the offer stage may be asked to attend an in-person interview at a hirify.global office or hub.
• Employment may be conditioned on eligibility to receive technology controlled under U.S. export laws without sponsorship for an export license.