Job Description
About the Role
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.
What You’ll Do
Design and build AI agents from scratch to production — systems that detect, fix, and validate vulnerable components automatically
Develop and maintain infrastructure to support agent operations at scale [AIOps], including context management, evaluations and orchestration
Create agentic workflows that enable multiple agents to collaborate and reason jointly
Build tools and utilities that agents use (e.g., for image inspection, diff generation, static analysis)
Implement evaluation and performance measurement methods for agent reliability and accuracy
Develop hybrid and vector database applications for retrieval and context management
Build and integrate AI-related apps such as MCP-based systems, chat interfaces, and standalone agent utilities
Instrument all experiments with tracing, observability, and structured metrics for reproducibility
Must Have
5+ years of hands-on experience in software engineering, preferably with exposure to AI-driven products or infrastructure
Strong proficiency in Python for backend systems, tooling, and AI integration
Solid foundation in software engineering, infrastructure, and cloud environments
Proven experience working 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
Experience designing or orchestrating multi-agent systems or agentic workflows
Awareness of context management techniques and prompt/tool/validation loop design
Nice to Have
Go experience, especially for rebuilding binaries or low-level utilities
Experience with Argo, Kubernetes, or other orchestration systems
Background in evaluation frameworks or agent performance measurement
Experience with code-focused AI agents, developer tools, or AppSec/security automation
Familiarity with vector databases, RAG pipelines, and graph-based context construction
Understanding of DevSecOps, AppSec, or software supply chain security concepts