Lead AI Security Engineer
Core
Design, build, and deploy autonomous AI agents and multi-agent systems for an Agentic Security Operations Center (SOC) to perform autonomous triage, semantic correlation, and proactive threat mitigation.
Role type
Lead IC AI Security Engineer (Agentic SOC)
Builds
Production-grade, proprietary multi-agent systems integrating with enterprise security stacks (SIEM, EDR, XDR)
Domain
Cybersecurity / Generative AI / Cloud Infrastructure
Deliverable
production ML models
Required skills
Python, Large Language Models (LLMs), Cloud platforms (AWS, Google Cloud, Azure), Software Engineering, Security domain knowledge, Retrieval-Augmented Generation (RAG), Human-in-the-Loop (HITL) design, LLM security (prompt injection, data poisoning mitigation)
Preferred skills
Multi-agent orchestration frameworks (LangChain, LlamaIndex, AutoGen, CrewAI), Vector Databases (Pinecone, Qdrant, Milvus, Weaviate), REST APIs/Webhooks for security platforms, Containerized cloud environments (Kubernetes/EKS/AKS), Fine-tuning methodologies (LoRA, QLoRA)
Technologies
Python, AWS, Google Cloud, Azure, LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, Pinecone, Qdrant, Milvus, Weaviate, Splunk, CrowdStrike, Microsoft Sentinel, Palo Alto XSOAR, Kubernetes, EKS, AKS, Llama 3, Mistral
Responsibilities
Design, test, and deploy autonomous AI agents integrating with security stacks; Translate SOC playbooks into deterministic agentic pipelines; Optimize RAG workflows for real-time security context; Evaluate and optimize LLM performance, latency, and cost; Engineer Human-in-the-Loop handoff mechanisms; Implement security boundaries for LLM architecture against prompt injection and model abuse
Seniority
Lead, hands-on IC with strategic ownership