Offensive Security Engineer, Red Team

What you'll do

• Execute offensive security assessments and red team operations against AI-enabled applications and autonomous agents.
• Identify, weaponize, and validate vulnerabilities in LLM-based architectures including prompt injection and data exfiltration.
• Map and exploit abuse paths within multi-agent workflows to identify privilege escalation and cross-agent manipulation.
• Design, build, and deploy custom attack tooling to improve red teaming and application security operations.
• Develop AI-driven offensive agents to enhance internal security testing capabilities.
• Test, bypass, and exploit LLM integrations and agentic workflows across games and services.
• Document complex vulnerability chains found in modern applications, APIs, and cloud services.

What we're looking for

• 3+ years of experience in offensive security, red teaming, penetration testing, or advanced application security.
• Experience identifying, validating, and documenting complex vulnerabilities and exploit chains in modern applications, APIs, or cloud services.
• Experience testing, bypassing, or exploiting AI-enabled systems, LLM integrations, or agentic workflows.
• Proficiency in building custom exploit scripts or security tools using Python, Go, JavaScript, or similar languages.