Outcome Engineer - Experienced Professional

Consequential Work. Dedicated People. About Onebrief Onebrief builds collaboration and AI-powered workflow software for military planning and operational coordination. Military planning is complex by nature, requiring teams to coordinate information, people, and decisions across systems and locations. Onebrief brings planning, collaboration, simulation, and AI into one connected environment, helping teams test strategies, adapt to changing conditions, and make decisions with greater clarity when the stakes are real. We are a distributed team of builders from military, operational, and technology backgrounds who care deeply about improving how important work gets done. Some team members work remotely, while others work directly alongside customers in operational environments around the world. Founded in 2019, Onebrief is backed by leading investors including General Catalyst, Battery Ventures, Insight Partners, Sapphire Ventures, and Human Capital. Valued at more than $2 billion, we continue to invest in product innovation, AI capabilities, and team growth. We are also defining the future of software development. We believe the era of "human bandwidth" as the primary constraint on software delivery is ending. We are building a dedicated team to transition our organization from Software Engineering to Outcome Engineering. About The Role You’re a world-class software engin [... source excerpt omitted ...] tion that AI unlocks. As an Outcome Engineer at Onebrief, you’ll join the team inventing our AI Engineering Platform. This is neither just prompt building nor model development. You will be part of a team building the factory that builds the software. You will help move us from a world of managed backlogs to a world of infinite execution, creating the foundation of what product development becomes in an agentic world. We are looking for pioneers. What You'll Do Architect Multi-Agent Systems: Design the orchestration layers that enable multiple specialized agents to collaborate, debate, and execute complex tasks reliably. You will move us from simple prompts to robust, statef [... source excerpt omitted ...] ntext and Memory: Build the semantic infrastructure (knowledge graphs, vector stores) that provides agents with deep, structural understanding of our codebase and business intent. You will solve the "blank slate" problem for autonomous workers. Build Rigorous Evaluation Frameworks: Develop the testing harness that defines success. You will move us beyond "vibes" to deterministic validation of agentic outputs using formal specifications and automated metrics. Design Self-Healing Loops: Connect observability data directly to agent actions, enabling systems that not only detect failures but autonomously analyze and remediate them. Prototype and Deploy: We prove success by shippin