Were looking for a hands-on AI Enginee to build and own the agentic workflows at the heart of our security intelligence engine. This is abackend-focused engineering role: youll design, build, and maintain the autonomous systems that execute security workflows end-to-end - taking capabilities from research prototype to scalable, production-grade infrastructure.Youll be working at the edge of applied AI, turning LLMs and agentic frameworks into reliable, observable systems that operate in real customer environments.What Youll Build:Agentic Workflows (Core Focus): Design and maintain the orchestration backbone for multi-step, autonomous agents that investigate, reason about, and act on complex security operations.Internal AI Infrastructure: Contribute to a shared platform for models, data pipelines, training, evaluation, and observability that the whole AI team builds on.Responsibilities:Build and maintain the agentic workflow engine - orchestration, tool use, state management, retries, and evaluation - that powers our AI-driven security features.Develop the backend services and APIs that deploy AI capabilities safely and at scale.Collaborate with AI Researchers to translate findings into production-grade autonomous workflows.Own reliability, observability, and performance of the agentic systems in production.Requirements: Mid-to-senior engineering experience, or relevant technical military experience.Strong backend engineering background with a focus on ML/AI systems.Hands-on experience building with LLMs and agentic frameworks in production.Comfort operating in a fast-paced environment, bridging research and product engineering.Strong Advantages:Experience with LangChain / LangGraph (or comparable agent-orchestration frameworks) - a significant plus for this roleExperience with evaluation frameworks and observability for non-deterministic AI systems.This position is open to all candidates.
מתעניינים במשרה הזו?
