OneBrief
Outcome Engineer - Orlando, FL
About this role
Onebrief is seeking an Outcome Engineer to pioneer AI-powered software development by building multi-agent systems, governance frameworks, and autonomous workflows. You'll architect the infrastructure that enables AI agents to collaborate, execute complex tasks reliably, and replace traditional software development constraints with intelligent automation.
What you'll do
- Design and orchestrate multi-agent systems that collaborate on complex tasks with robust, stateful workflows
- Build governance and policy engines that enable autonomous systems to operate safely and at scale
- Engineer semantic infrastructure (knowledge graphs, vector stores) to provide agents with deep codebase understanding
- Develop rigorous evaluation frameworks and automated metrics for validating agentic outputs
- Create self-healing loops that connect observability to autonomous remediation
- Rapidly prototype and deploy agentic tools to production for internal teams and customers
What they're looking for
- Multi-agent system architecture and orchestration
- AI/LLM model understanding and application
- Software engineering and systems design
- Knowledge graphs and vector database implementation
- Evaluation frameworks and formal specifications
- Production deployment and DevOps
- Complex problem decomposition
- Observability and monitoring systems
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
OneBrief
OneBrief builds AtomEngine, an AI-powered cloud-based simulation platform designed for military training and operational exercises in classified and live environments. The company is hiring Software Development Engineers in Test, Gameplay Engineers, and Customer Success Engineers to support quality assurance, platform development, and direct customer deployment and support.
View all jobs at OneBriefLikely interview questions
- Tell us about your experience with multi-agent systems or orchestration platforms—what challenges did you encounter and how did you solve them?
- How would you approach designing guardrails for an autonomous agent operating in a safety-critical domain?