Staff Software Engineer, Gustie Assist

Gustie Assist builds Otto, the AI agent that Gusto's support advocates rely on to solve customers' hardest payroll, benefits, and compliance problems. When a small business hits a wall and reaches out, the advocate turns to Otto: it reasons over the customer's full context, answers in the moment, and increasingly takes real actions across Gusto's systems on the advocate's behalf to make the customer whole. We're a small platform team building an agent that reasons, acts, and has to get it right when the stakes are someone's payroll.

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

Here's what we're looking for:

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