AI Engineer – Build Security Automation Agents

About the role

We are looking for an AI Engineer to create production‑grade AI agents that automate vulnerability investigation, generate and validate code fixes, and continuously improve their performance. You will work at the intersection of large‑language‑model engineering, security automation, and rigorous evaluation to turn cutting‑edge research into reliable tools for developers.

Key responsibilities

• Design and maintain AI agent pipelines for CVE research, patch generation, container image remediation, and end‑to‑end merge requests.
• Define prompts, tool integrations, model selection, context handling, guardrails, and workflow integrations.
• Build feedback loops: trace production runs, create datasets, define evaluations and scorers, and use results to guide iteration.
• Analyze real‑world performance metrics such as patch success rate, quality, latency, and cost.
• Deploy and operate services on Kubernetes, Argo Workflows, AWS, and GitOps environments.
• Collaborate closely with product and engineering teams to prioritize high‑impact security problems and ship quickly.

Required profile

• Hands‑on experience building with LLMs and agentic architectures (e.g., LangGraph, Claude Agent SDK, OpenAI Agents SDK).
• Proficiency using coding agents such as Claude Code, Codex, or Cursor in daily engineering work.
• Strong understanding of data‑science mechanics: evaluation design, experimental rigor, statistical reasoning, and feedback loops.
• Ability to distinguish impressive demos from production‑ready systems.
• Experiment‑driven software engineering mindset: hypothesize, build, measure, learn, iterate.
• Comfort working independently in a fast‑moving, high‑ownership environment.

Required skills

• LangGraph
• Claude Agent SDK
• OpenAI Agents SDK
• Claude Code
• Codex
• Cursor
• Kubernetes
• Argo Workflows
• AWS
• GitOps