Outcome Engineer: Architect Multi-Agent AI Systems

Onebrief; United States; À distance; USD 180 000 - 240 000; Plein temps

Résumé du poste

Onebrief seeks a world-class software engineer to join its AI Engineering Platform team, moving beyond prompts to build the factory for agentic software. You will contribute to the evolution from software engineering to Outcome Engineering, shaping intelligent, autonomous systems used in real-world environments.

You will collaborate across disciplines to design, test, and deploy agentic tools, APIs, and governance mechanisms for safe, scalable AI-driven workflows.

Qualifications

• Investor-backed startup environment with a focus on AI and agentic systems.
• Experience shipping products and platforms, not just prototypes.
• Ability to work across diverse disciplines and collaborate asynchronously.

Responsabilités

• Architect Multi-Agent Systems: design orchestration for multiple agents to collaborate and execute tasks.
• Implement Automated Governance: build guardrails and policy engines for autonomous systems.
• Engineer Context and Memory: develop semantic infrastructure like knowledge graphs and vector stores.
• Build Rigorous Evaluation Frameworks: create testing harness with deterministic validation.
• Design Self-Healing Loops: connect observability data to agent actions for remediation.
• Prototype and Deploy: rapidly prototype tools and deploy to production for internal and customers.
• Experiment and Learn: work with new models and orchestration techniques daily.

Connaissances

Software Engineer

AI Researcher

Game Engineer

Product Manager

Platform/SRE Engineer

Designers

Agentic Pioneer

Outils

Node.js

TypeScript

PostgreSQL

Redis

Kubernetes

AWS

Description du poste

Onebrief seeks a world-class software engineer to join its AI Engineering Platform team, moving beyond prompts to build the factory for agentic software. You will contribute to the evolution from software engineering to Outcome Engineering, shaping intelligent, autonomous systems used in real-world environments.

You will collaborate across disciplines to design, test, and deploy agentic tools, APIs, and governance mechanisms for safe, scalable AI-driven workflows.