Job Description

Upwind is a next-generation Cloud Security Platform that leverages runtime context to identify and prioritize critical risks, providing precise insights and efficient cloud security management. Unlike traditional tools, Upwind uses runtime data proactively for risk prioritization and posture insights, ensuring teams focus on what truly matters. With industry-leading efficiency and eBPF-powered sensors, Upwind delivers comprehensive capabilities, including agentless cloud posture discovery, real-time threat protection, and integrated API security. From misconfigurations to malware defense, Upwind ensures end-to-end, cost-effective cloud infrastructure protection. At Upwind, you’ll have the opportunity to think creatively, explore new ideas, and use your skills to make a meaningful impact on our growth.

We’re looking for a hands-on **AI Engineer** to build and own the agentic workflows at the heart of our security intelligence engine. This is a **backend-focused engineering role**: you’ll design, build, and maintain the autonomous systems that execute security workflows end-to-end — taking capabilities from research prototype to scalable, production-grade infrastructure.

You’ll be working at the edge of applied AI, turning LLMs and agentic frameworks into reliable, observable systems that operate in real customer environments.

What You’ll 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 role
• Experience with evaluation frameworks and observability for non-deterministic AI systems.