AI Engineer

<h3>About the Role</h3> <p>We’re building the first autonomous AI platform that can automatically detect, fix, and validate software vulnerabilities — end to end, at scale. Think of it as agents that can update dependencies, edit Dockerfiles, rebuild Go binaries with patched versions, and validate everything automatically. This is a deeply technical, research-driven role where you’ll design, implement, and scale AI agent systems that operate on real codebases. You’ll work at the intersection of backend engineering, AI systems, and application security — designing agents, context pipelines, and evaluation frameworks that bring autonomous reasoning to production.</p> <h3>What You’ll Do</h3> <ul> <li>Design and build&nbsp;<strong>AI agents from scratch to production</strong>&nbsp;— systems that detect, fix, and validate vulnerable components automatically</li> <li>Develop and maintain&nbsp;<strong>infrastructure to support agent operations at scale [AIOps]</strong>, including context management, evaluations and orchestration</li> <li>Create&nbsp;<strong>agentic workflows</strong>&nbsp;that enable multiple agents to collaborate and reason jointly</li> <li>Build&nbsp;<strong>tools and utilities</strong>&nbsp;that agents use (e.g., for image inspection, diff generation, static analysis)</li> <li>Implement&nbsp;<strong>evaluation and performance measurement methods</strong>&nbsp;for agent reliability and accuracy</li> <li>Develop&nbsp;<strong>hybrid and vector database applications</strong>&nbsp;for retrieval and context management</li> <li>Build and integrate&nbsp;<strong>AI-related apps</strong>&nbsp;such as MCP-based systems, chat interfaces, and standalone agent utilities</li> <li>Instrument all experiments with tracing, observability, and structured metrics for reproducibility</li> </ul> <h3>Must Have</h3> <ul> <li>5+ years of hands-on experience in software engineering, preferably with exposure to AI-driven products or infrastructure</li> <li>Strong proficiency in <strong>Python</strong>&nbsp;for backend systems, tooling, and AI integration</li> <li>Solid foundation in&nbsp;<strong>software engineering, infrastructure, and cloud environments</strong></li> <li>Proven experience working with&nbsp;<strong>LLMs and AI agents</strong>&nbsp;in applied settings</li> <li>Familiarity with&nbsp;<strong>LangGraph, LangChain, OpenAI, Claude Code, and Cursor</strong>&nbsp;frameworks</li> <li>Strong understanding of&nbsp;<strong>Docker</strong>&nbsp;and containerized development workflows</li> <li>Experience designing or orchestrating&nbsp;<strong>multi-agent systems</strong>&nbsp;or&nbsp;<strong>agentic workflows</strong></li> <li>Awareness of&nbsp;<strong>context management techniques</strong>&nbsp;and prompt/tool/validation loop design</li> </ul> <h3>Nice to Have</h3> <ul> <li><strong>Go</strong>&nbsp;experience, especially for rebuilding binaries or low-level utilities</li> <li>Experience with&nbsp;<strong>Argo, Kubernetes</strong>, or other orchestration systems</li> <li>Background in&nbsp;<strong>evaluation frameworks</strong>&nbsp;or&nbsp;<strong>agent performance measurement</strong></li> <li>Experience with&nbsp;<strong>code-focused AI agents</strong>,&nbsp;<strong>developer tools</strong>, or&nbsp;<strong>AppSec/security automation</strong></li> <li>Familiarity with&nbsp;<strong>vector databases</strong>,&nbsp;<strong>RAG pipelines</strong>, and&nbsp;<strong>graph-based context construction</strong></li> <li>Understanding of&nbsp;<strong>DevSecOps, AppSec</strong>, or&nbsp;<strong>software supply chain security</strong>&nbsp;concepts</li> </ul>