Key Responsibilities
- Design and develop scalable, high-performance AI systems for autonomous detection, RAG-backed investigation, and auto-remediation workflows
- Productionize large-scale LLMs, graph-based reasoning engines, and streaming feature pipelines handling billions of security events
- Own evaluation and reliability frameworks, including prompt libraries, fine-tuning, red-team testing, latency budgets, and fallback strategies
- Mentor AI engineers, conduct design reviews, enforce code quality, and instill a security-first mindset
- Collaborate with Product, Detection Engineering, and Customer Success to translate attacker behavior into robust ML and rule-based detections
- Experiment with retrieval-augmented generation, tool-calling agents, and multi-modal models (text + logs + graphs)
Requirements
- 10+ years in software development with expertise in Python, Go, Rust, or Java
- Deep knowledge of LLM architecture, prompt engineering, and vector database workflows
- Hands-on experience building agents, orchestration frameworks (LangChain/LangGraph, Agno AGI), and evaluation harnesses
- Strong fundamentals in microservices architecture, containerization (Docker, Kubernetes), and event-driven systems
- Proven ability to lead teams and drive technical innovation in high-growth environments