What You’ll Do

• Own our multi-modal AI stack from OSINT agents to voice agents delivering realistic social engineering attacks
• Build MCP servers to enhance agent capabilities and architect agentic memory layers for optimal context delivery
• Develop agent evaluation frameworks and fine-tune SLMs to optimize social engineering campaign outputs
• Deploy production AI agents using vector and graph databases, LLM observability stacks, and modern orchestration tools
• Research and publish on multi-agent systems best practices
• A bit of everything.. Plain software engineering, data, etc.

Requirements

• Healthy skepticism of AI-generated code and proficiency in getting the most out of AI-assisted coding while remaining a critical thinker
• Strong Engineering fundamentals, this role is for someone that can work autonomously across the stack with a heavy lean towards applied AI
• Deep expertise in Python and Go for building scalable backend systems
• Strong experience with vector databases, graph databases, context engineering, and agentic memory/orchestration
• Hands-on experience operating and leveraging  LLM observability stacks
• Proficiency with containerization (Docker) and orchestration (Kubernetes, AWS)
• Experience with major cloud providers (AWS) and CI/CD best practices
• Commitment to writing high-quality, maintainable, and well-tested code

Your Impact

• Define the next generation of AI-native security validation at enterprise scale
• Protect hundreds of thousands of employees at Fortune 500 companies from social engineering attacks
• Work at the cutting edge of multi-agent systems and security research
• Own entire AI features from research to production with no bureaucracy
• Shape engineering culture and practices as we grow