engineering
Posted 2 weeks agoStaff Software Engineer, Core AI Platforms
at Gusto
San Francisco, United StatesHybrid
Responsibilities
- Design and maintain evaluation frameworks across offline and online environments — including golden datasets, LLM-as-judge pipelines, and production replay — while establishing regression gates and end-to-end observability and tracing for agent runs
- Design, build, and test Gusto core platform services – communications, reporting, dashboards, access, workflows, risk, payments, and compliance capabilities, among others
- Collaborate with our Product Engineering, Product Management, Data, and Design teams to understand customer pain points, come up with solutions, and then prototype, iterate, and launch daily
- Build platforms that engineering teams rely on, and trust to deliver products that our customers genuinely love
Requirements
- AI is a fundamental part of how work gets done at Gusto. We expect all team members to actively engage with AI tools relevant to their role and grow their fluency as the technology evolves. AI experience
- We're looking for seasoned full-stack software engineers to join the teams behind Gusto's AI product platforms — the shared systems that our product teams build upon — to serve small business owners every day.
- As a Staff Software Engineer, you'll operate across the full lifecycle of foundational systems: deliver production AI agent systems — multi-agent orchestration, tool/workflow registries, agent-to-agent handoffs, human-in-the-loop escalation, and long-running conversation state, shaping architecture early in the design process, building self-service internal features and APIs, and owning their performance long after launch.
- Help scale one of the largest Ruby/Rails and Javascript/React applications in the world
- experience taking AI/LLM capabilities to production — agent orchestration, tool integration, retrieval, and evaluation/feedback loops that keep AI improving safely
- AI fluency: fluent, daily use of AI coding assistants (e.g., Claude Code, or equivalent AI harness) across the development lifecycle — writing, reviewing, debugging, and documenting code — with strong judgment on when to apply them, how to evaluate output quality, and how to stay current as the tooling evolves
- Curiosity and experimentation with emerging AI frameworks, applying and sharing best practices to evaluate and scale AI use safely across teams Others: •
- Experience in, or interest working in, Ruby on Rails
- Ability to build well-structured, maintainable, well-documented code
- Ability to effectively communicate across engineering teams and with business stakeholders
Experience
- Successful applicants typically have 8+ years of software development experience
Benefits
- We handle the hard stuff — payroll, health insurance, 401(k)s, and HR — so owners can focus on their craft and their customers.
- All full-time employees receive competitive base pay, benefits, and equity (RSUs) — because everyone who helps build Gusto should share in its success.
- Our cash compensation amount for this role is targeted at $163,000–$204,000 in Denver & most remote locations, and $197,000–$247,000 for San Francisco & New York.
- Stock equity is additional.
Additional details
- At Gusto, we're on a mission to grow the small business economy.
- With teams in Denver, San Francisco, and New York, we support more than 500,000 small businesses nationwide and are building a workplace that reflects the people we serve.
- Offer amounts are determined by role, level, and location.
- Learn more about our Total Rewards philosophy .
- requirements vary by role and will be assessed during the interview process. About the Role:
- That means engineering the core business engine, enabling product teams with reliable backend services, and setting the engineering standard for those around you.
- If you're drawn to work that combines technical craft with real-world impact — helping power the livelihoods of millions using Gusto products — join us!
- Mentor other engineers to help solve some of the hardest technical problems out there in very complex domains and at a large scale
- Passion for creating scalable, efficient platforms for users
- Appreciation for a collaborative, test-driven environment