Staff Software Engineer, Gustie Assist
Gusto · Denver, CO - Hybrid; New York, New York, United States; San Francisco, CA - Hybrid
About this role
**Staff Software Engineer — Gustie Assist (Otto AI Agent)** **About Gusto** Gusto is on a mission to grow the small business economy. We handle the hard stuff—payroll, health insurance, 401(k)s, and HR—so owners can focus on their craft and their customers. With teams in Denver, San Francisco, and New York, we support 500,000+ small businesses nationwide and are building a workplace that reflects the people we serve. All full-time employees receive competitive base pay, benefits, and equity (RSUs). Offer amounts are determined by role, level, and location. Gusto also expects team members to actively engage with AI tools relevant to their role and grow their fluency as the technology evolves. --- **About Gustie Assist** Gustie Assist builds **Otto**, the AI agent that Gusto support advocates rely on to solve customers’ hardest payroll, benefits, and compliance problems. When a small business hits a wall, 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. This is broad, hands-on applied AI work. You’ll own an **LLM agent runtime** and the full stack around it—tool/action layer, Rails/GraphQL backend, advocate-facing frontend, and an eval system that keeps it trustworthy while it touches live customer accounts. --- **Day-to-day** - Design and build across the Otto platform (runtime + agent graph, tool/action layer, Rails/GraphQL backend, advocate-facing experience), owning a meaningful slice end-to-end. - Expand what the agent can safely do with autonomous, tool-using actions and **human-in-the-loop** approval, backed by secure, auditable identity and permissions. - Build **eval and observability systems** (LLM-as-judge + deterministic scorers, offline gates, and online production monitoring) to ship weekly changes without regressing correctness or escalation behavior. - Work directly with LLMs: prompting, tool/function design, retrieval, and feedback loops that improve Otto from real advocate interactions. - Partner with Product, Data, Design, and CX to turn advocate/customer pain into shipped capabilities. - Mentor engineers and set the bar for building agentic systems responsibly and at scale. --- **What we’re looking for** - Typically **8+ years** of software engineering experience, owning systems end-to-end. - Shipped **LLM-powered or agentic systems** in production (tool-calling/agents, retrieval, evals) and know where they break and how to make them reliable. - Strong full-stack range—comfortable moving between backend services, an LLM runtime, and customer-facing product. - Experience owning multi-quarter projects that deliver 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. --- **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** (or ability to ramp quickly). - Familiarity with **GraphQL** and federated backends. - Appreciation for a collaborative, test-driven, high-autonomy environment and clear communication. --- **Location / Office expectations** Gusto has offices in **Denver, San Francisco, and New York City**. Employees based in those locations are expected to work from the office on designated days
Listing freshness
CronJobs last confirmed this listing 17h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.