> Markdown version of [/jobs/ext/3958258-staff-software-engineer-gustie-assist](https://www.wearedevelopers.com/jobs/ext/3958258-staff-software-engineer-gustie-assist). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Software Engineer, Gustie Assist

- **Company:** Gusto
- **Location:** San Francisco, CA, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** JavaScript (Programming Language), Artificial Intelligence, Acceptance Test-Driven Development, Ruby on Rails, Software Engineering, ReactJS, Large Language Models, Backend, Agentic-AI, Build Management, Graphql, Front End Software Development, Multiplatform
- **Published:** October 27, 2026
- **Apply:** https://www.careerbuilder.com/job-details/staff-software-engineer-gustie-assist-san-francisco-ca--94cddc94-4f75-48d5-8813-34e4f636efd1

## About the Role

Software Engineering, Insurance, Small Business, Business Growth, Philosophy, Artificial Intelligence (AI), GraphQL, SLICE (Simulation Language with Integrated Circuit Emphasis), Multiplatform/Cross-Platform, Production Control, * Typically 8+ years of software engineering experience, owning systems end-to-end

 * You''ve built and shipped LLM-powered or agentic systems in production, including tool-calling/agents, retrieval, or evals, and you know where they break and how to make them reliable
 * Strong full-stack range. Must be comfortable moving between backend services, an LLM runtime, and customer-facing product, and picking up whatever the problem needs
 * Experience owning multi-quarter projects that make measurable user impact at scale
 * Sound judgment about safety and blast radius when software takes real actions on real accounts
 * Ability to mentor engineers and raise the bar around you

Also great to have:

 * Experience with agent frameworks, evals/LLM-as-judge, retrieval, or MCP-style tool architectures
 * Experience with Ruby on Rails and/or JavaScript/React (our stack), or the ability to ramp quickly
 * Familiarity with GraphQL and federated backends
 * Appreciation for a collaborative, test-driven, high-autonomy environment, and clear communication with engineering and business stakeholders

## Description

This is unusually broad, hands-on applied-AI work: you''ll own an LLM agent runtime and the full stack around it, including the tool layer that lets it act over Gusto''s systems, the Rails/GraphQL backend, the advocate-facing frontend, and the eval system that keeps it trustworthy while it touches live customer accounts. We keep the path from idea to production short, and measure ourselves on customer outcomes, not model novelty.

Here''s what you''ll do day-to-day:

 * Design and build across the Otto platform, including the runtime and agent graph, the tool/action layer, the Rails/GraphQL backend, and the advocate-facing experience, owning a meaningful slice end-to-end
 * Expand what the agent can safely do: autonomous, tool-using actions with human-in-the-loop approval, built on a secure, auditable identity and permissions model
 * Build the eval and observability systems (LLM-as-judge + deterministic scorers, offline gates and online production monitoring) that let us change the agent in production weekly without regressing correctness or escalation behavior
 * Work directly with LLMs, including prompting, tool/function design, retrieval, and the feedback loops that turn real advocate interactions into a better Otto
 * Partner closely with Product, Data, Design, and our CX teams to turn advocate and customer pain into shipped capabilities
 * Mentor engineers and set the bar for how we build agentic systems responsibly and at scale