Tech Stack

Description

You will design, implement, and scale AI agent systems that automatically detect, fix, and validate software vulnerabilities. You'll work at the intersection of backend engineering, AI systems, and application security, building agents and evaluation frameworks for autonomous code reasoning.

Requirements

• 5+ years of hands-on software engineering experience, preferably with AI-driven products
• Strong proficiency in Python for backend systems, tooling, and AI integration
• Proven experience with LLMs and AI agents in applied settings
• Familiarity with LangGraph, LangChain, OpenAI, Claude Code, and Cursor frameworks
• Strong understanding of Docker and containerized development workflows

Responsibilities

• Design and build AI agents to detect, fix, and validate vulnerable components automatically
• Develop infrastructure for agent operations at scale including context management, evaluations, and orchestration
• Create agentic workflows for multi-agent collaboration and reasoning
• Build tools for image inspection, diff generation, and static analysis
• Implement evaluation and performance measurement methods for agent reliability