Staff Software Engineer, Agent Harnessing

Scout AI is developing Fury, a robotic foundation model for defense. The Staff Software Engineer will build the architecture and platform that enables AI agents to control physical systems, including agent orchestration, hardware integration, simulation environments, and model-training data pipelines.

Responsibilities:

• Designing and advancing the agent harness (agent loop, tools, prompts, execution environment, capabilities) used across Scout AI's agentic stack
• Integrating fullstack software with physical hardware systems and AI agents, ensuring robust, low-latency communication across complex pipelines
• Building simulation environments and video-game-like frameworks that allow agents to be tested and trained before physical deployment
• Owning the connectors between AI models and real-world systems, the layer that translates model output into physical action
• Fine-tune frontier AI models and build the data acquisition pipelines that feed the training infrastructure powering our agents
• Work shoulder-to-shoulder with warfighters to turn capability requests into production-ready agentic systems

Requirements:

• 10+ years of full-stack engineering experience
• You have built complex agentic products or infrastructure—agent loops, orchestration systems, tool-use frameworks
• You have strong opinions on model and agent behavior
• You are a systems-oriented fullstack engineer with hands-on experience integrating software with physical hardware or low-level systems
• You have exposure to simulation environments, game engines (Unreal, Unity, Isaac Sim), or robotics middleware (ROS/ROS2)
• You have strong SWE fundamentals—architecture, distributed systems, real-time pipelines—and love shipping production systems
• Must be a U.S. Person due to required access to U.S. export controlled information or facilities
• Passion about defense of the United States and its allies
• May be expected to obtain and hold a U.S. Top Secret security clearance
• (startup or high-ownership environment preferred)