SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Onebrief builds AI-powered collaboration and workflow software for military planning and operational coordination. The company, founded in 2019 and valued at over $2 billion, is backed by leading investors including General Catalyst, Battery Ventures, and Sapphire Ventures.
As an Outcome Engineer, you will join a pioneering team inventing Onebrief's AI Engineering Platform. This role sits at the intersection of software engineering and AI systems design—moving beyond simple prompt engineering to build the infrastructure that enables autonomous, agentic software development at scale.
Key responsibilities include:
- Architect multi-agent systems that enable specialized agents to collaborate, debate, and execute complex tasks reliably, transitioning from simple prompts to robust, stateful agentic workflows.
- Implement automated governance and policy engines that allow autonomous systems to operate safely at speed, replacing manual review with programmatic constraints.
- Engineer context and memory infrastructure (knowledge graphs, vector stores) that provides agents with deep structural understanding of codebases and business intent.
- Build rigorous evaluation frameworks that move beyond subjective validation to deterministic testing of agentic outputs using formal specifications and automated metrics.
- Design self-healing loops that connect observability data to agent actions, enabling systems to autonomously detect, analyze, and remediate failures.
- Rapidly prototype and deploy new agentic tools to production for both internal teams and customers.
- Experiment continuously with new models, orchestration techniques, and validation approaches in this emerging field.
The team is distributed but high-bandwidth, with members working remotely and some embedded in operational environments globally. Collaboration is intense and often synchronous.
Core tech stack: Large Language Models, Vector Databases, Node.js, TypeScript, PostgreSQL, Redis, Kubernetes, AWS.
REQUIREMENTS:
The company seeks diverse backgrounds and emphasizes that the best Outcome Engineers may come from non-traditional paths. Candidates may include:
- Software Engineers: Coders ready to automate their own work, viewing code as a liability and outcomes as the asset.
- AI Researchers: Deep understanding of models with desire to apply them to messy, real-world production systems; expertise in emergent behavior and multi-agent coordination.
- Game Engineers: Experience building complex simulations or games; understanding of rules, entities, and validation logic for autonomous agents.
- Product Managers: Obsessive about products, excellent at translating ambiguous needs into rigorous deliverables.
- Platform/SRE Engineers: View infrastructure as a product; expert in observability, reliability, and automation.
- Designers: Comfortable creating with technology; focused on building humane agentic systems.
- Agentic Pioneers: Regardless of background, must have already built agents, hit the limits of frameworks like LangChain or AutoGen, and have strong opinions on orchestrating reliable reasoning.
Non-negotiable requirements:
- Must be a product builder with a history of shipping; understand the difference between prototypes and production systems users rely on.
- Must be an active agentic builder—not theoretical. Built with agents recently and actively building now; familiar with real-world frustrations of agent development.
- Must love intense collaboration; comfortable with high-bandwidth, often synchronous remote work; willing to engage deeply with teammates.
- Must respect expertise without gatekeeping; value sharing knowledge and empowering others across disciplines.
- Must write clearly to think; demonstrate clarity through documentation of experiments, architectural decisions, and failures.
