Outcome Engineer - Salt Lake City, UT

Onebrief • Salt Lake City, UT

7d • $200,000 - $320,000 • Remote

About The Position

Onebrief is seeking pioneers to join the team inventing our AI Engineering Platform. This role is for a world-class software engineer who is ready to reinvent themselves and embrace the power of AI. As an Outcome Engineer, you will be part of a team building the 'factory that builds the software,' moving from managed backlogs to infinite execution and shaping the future of product development in an agentic world. This is a creation role where learning happens by building, prototyping, and deploying new agentic tools to production for both internal teams and customers.

Requirements

• Strong software engineering skills are valuable.
• Interdisciplinary backgrounds and an embrace of ego-free collaboration are key.
• You are a coder who is ready to automate your own job, seeing code as a liability and outcomes as the asset.
• You love building products, tools, platforms, and force multipliers.
• You understand AI models at a deep level but want to apply them to messy, real-world production systems.
• You care about emergent behavior and multi-agent coordination.
• You have strong opinions about world models.
• Experience building complex simulations or games, understanding how to define rules, entities, and validation logic for autonomous agents.
• Obsessive about products, excelling at translating ambiguous user needs into rigorous deliverables and managing complexity.
• Expertise in observability, reliability, and automation, wanting to apply o11y to probabilistic AI systems.
• Not afraid to create with technology and care deeply about building agentic systems that make more humane products and decisions.
• Have already built your own agents and hit the limits of frameworks like LangChain or AutoGen, with strong opinions on orchestrating reliable reasoning.
• Must have a history of shipping products; understanding the difference between a prototype and a relied-upon product.
• Must have built with agents recently and understand the frustrations of prompt instability.
• Must be comfortable with intense, high-bandwidth collaboration, often synchronously.
• Must be willing to share expertise and empower others, avoiding silos.
• Must write to think, demonstrating clarity of thought through clear writing, documenting experiments, architectural decisions, and failures.

Responsibilities

• Architect Multi-Agent Systems: Design orchestration layers for specialized agents to collaborate, debate, and execute complex tasks reliably, moving from simple prompts to robust, stateful agentic workflows.
• Implement Automated Governance: Create guardrails and policy engines for autonomous systems to operate safely at speed, building infrastructure that replaces manual review with programmatic constraints.
• Engineer Context and Memory: Build semantic infrastructure (knowledge graphs, vector stores) to provide agents with deep, structural understanding of codebase and business intent, solving the 'blank slate' problem for autonomous workers.
• Build Rigorous Evaluation Frameworks: Develop testing harnesses to define success, moving 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: Rapidly prototype new agentic tools and deploy them to production for internal teams and customers.
• Experiment and Learn: Experiment with new models, orchestration techniques, and validation methods for agent behavior daily.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed