Description
We are looking for a Lead AI Automation engineer to design and build advanced AI-driven automation that supports offensive security and security research workflows.
This is a deeply hands-on engineering role. You will work closely with the AI Automation Director and a small, agile team to implement orchestrated, agent-based automation—translating architectural direction into reliable, production-grade systems. The focus is on building automation that can reason over complex data, coordinate multi-step actions, and operate safely in real environments.
This role is ideal for an experienced engineer who has built real AI systems, understands their limitations, and wants to apply them to complex, adversarial problem spaces.
Key Responsibilities
Design, implement, and maintain agent-based AI automation workflows under the technical direction of the AI Automation Director
-
Build systems capable of:
Reasoning over large and heterogeneous data sources
Planning and executing multi-step workflows
Grounding actions in real-world data
Result-adaptive execution
-
Implement core components, including:
Agent logic and orchestration layers
Tool interfaces and execution handlers
State management, memory, and context handling
Translate high-level automation designs into robust, testable implementations
Integrate AI-driven workflows with existing services, data sources, and platforms
Implement observability, logging, and debugging mechanisms for AI-assisted systems
Participate in evaluation and iteration of prompts, workflows, and control logic
Collaborate closely with security practitioners to ensure outputs are actionable and operationally relevant
Contribute to engineering standards around safety, reliability, and change management
Required Qualifications
9+ years of professional software engineering experience, with strong exposure to AI-driven systems or automation
Hands-on experience with LLMs and agentic frameworks beyond basic prompt usage
-
Strong understanding of:
Agent orchestration and execution control
Task planning and decomposition
State, memory, and context management
Proven ability to build production-grade systems, not just prototypes
-
Strong software engineering fundamentals, including:
Modular system design
API integration
Distributed systems
Experience working in fast-moving, ambiguous problem spaces
Experience in offensive security, penetration testing, red teaming, application security, or vulnerability research with demonstrated technical skills
Ability to reason about failure modes and edge cases in semi-autonomous systems
Strong communication skills and ability to collaborate closely with senior technical leadership
Preferred Qualifications (Advantage)
Experience in security engineering, offensive security, or security research
-
Familiarity with:
Large-scale data ingestion and normalization
Signal correlation or prioritization systems
Workflow engines or automation platforms
-
Experience with:
Model evaluation or fine-tuning
Prompt optimization and structured prompting
Background in systems that operate across large, evolving external surfaces
Comfort balancing experimentation with production reliability