Security Researcher (Cybersecurity)

Location: Remote, US

Company

Applied AI lab building AI agents for cybersecurity, assessing enterprise data and developing autonomous security workflows in partnership with Fortune 500 companies.

What you will do

• Design and build red-team agents, including the agent harness, MCP servers, tools, and skills covering reconnaissance, payload development, delivery, Command and Control, and post-exploitation.
• Extend agents to full-chain attack operations across Windows, Active Directory, on-premises, cloud, and network environments, including initial access, evasion, privilege escalation, and lateral movement.
• Develop detection-evasion tradecraft and operate detonation and detection loops against real EDR solutions.
• Build and operate realistic cyber ranges with EDR, SIEM, and logging, initially focused on Windows and Active Directory and later extending to cloud and hybrid environments.
• Convert attack paths into benchmarks and evaluation tasks with verifiable success criteria, including benchmarks such as IntrusionBench.
• Verify critical and high-severity attack paths in customer environments and represent the company through research, talks, and open-source contributions.

Requirements

• 6+ years of experience in offensive security, red team operations, or adversary emulation.
• Hands-on experience running full-chain operations from initial access through post-exploitation across Windows, Active Directory, and on-premises environments.
• Depth in Command and Control frameworks such as Mythic, payload development, and detection evasion against EDR.
• Ability to write code, such as Python, to turn manual tradecraft into repeatable and automatable capabilities.
• Experience standing up and operating realistic test environments or cyber ranges with EDR, SIEM, and logging.

Nice to have

• Cloud attack experience involving identity and access management, misconfiguration, or CI/CD, or network attack experience.
• Experience building evaluations or benchmarks that measure security capability.
• Open-source tooling, conference talks, or published research in offensive security.
• Experience working with AI agents, LLM tooling, or agentic workflows.

Culture & Benefits

• Research combines frontier AI work with real-world cybersecurity execution.
• Work involves collaboration with cloud security researchers and Fortune 500 customers.
• Research contributions include talks and open-source work in the offensive security community.