Job Description
AI Security Engineer, Agentic SOC
Overview
Our client is pioneering the next generation of cyber defense by building an Agentic Security Operations Center, or SOC. Our mission is to move beyond reactive alerting by creating self-orchestrating, context-aware AI systems capable of autonomous triage, semantic correlation, and proactive threat mitigation. In this role, you will leverage emerging AI capabilities to reimagine how we defend the organization.
Team Description
The AI SOC Engineering team is at the center of bringing our vision for AI-driven security to life. This is a squad of builders operating at the intersection of Generative AI, software engineering, and offensive and defensive security. We do not just write scripts; we architect the intelligent fabric of our defensive posture.
We build and deploy production-grade, proprietary multi-agent systems that empower human analysts to manage complex incident response with autonomous AI agents in responsible and scalable ways.
In this role, you will:
● Build & Deploy Agents: Design, test, and deploy autonomous and semi-autonomous AI agents that integrate natively with our enterprise security stack, including SIEM, EDR, XDR, and threat intelligence feeds.
● Code the Playbooks: Translate traditional, human-centric SOC playbooks and analyst workflows into deterministic and heuristic agentic pipelines using DAGs and multi-agent routing.
● Optimize RAG Pipelines: Design, optimize, and maintain production-grade Retrieval-Augmented Generation, or RAG, workflows to inject real-time security context, network topology, and historical incident logs into agent prompts.
● LLM Performance Engineering: Continuously evaluate, benchmark, and optimize LLM performance, context window utilization, latency, and cost-efficiency across various models, including open-source and commercial models.
● Design Human-in-the-Loop, or HITL: Collaborate deeply with Tier 3 Analysts and Threat Hunters to engineer seamless HITL handoff mechanisms, ensuring agents safely escalate complex anomalies to humans.
● Secure the AI: Implement robust security boundaries around our LLM architecture, mitigating risks such as prompt injection, data poisoning, model tool-abuse, and addressing the OWASP Top 10 for LLMs.
The Ideal Candidate
● You are a Builder First: You take immense pride in shipping clean, production-grade, asynchronous code. You care about system architecture as much as model accuracy.
● Security-Curious or Security-Hardened: You bridge the gap between AI research and practical cybersecurity. You understand that an AI agent is only as good as the guardrails keeping it from deleting a production server during a false positive.
● Thrives in Ambiguity: Building an Agentic SOC means charting unknown territory. You love breaking down abstract, high-level security problems into concrete, execution-ready AI systems.
Basic Qualifications
● Bachelor's degree in Computer Science, Artificial Intelligence, Electrical Engineering, Computer Engineering, or a related field, plus at least 4 years of experience developing AI and ML algorithms or technologies; OR a Master's degree in a related field, plus at least 2 years of experience.
● At least 2 years of experience programming with Python, Go, Scala, or Java.
Preferred Qualifications
● 3 years of experience deploying scalable and responsible AI solutions on cloud platforms such as AWS, Google Cloud, or Azure.
● Experience designing, developing, delivering, and supporting AI services, specifically within the domains of security operations or threat intelligence.
● Hands-on experience building multi-agent or complex orchestration systems using tools such as LangChain, LlamaIndex, AutoGen, CrewAI, or Semantic Kernel.
● Proven experience working with production vector databases, such as Pinecone, Qdrant, Milvus, or Weaviate, for semantic chunking, embedding generation, and metadata filtering.
● Experience deploying and scaling AI workloads in containerized cloud environments, including AWS, Azure, or GCP using Kubernetes, EKS, or AKS.
Are you ready to build the future of autonomous, agentic defense?