Software Engineer, AgentOps

About the role

About Us:

Fieldguide is establishing a new state of trust for global commerce and capital markets by automating and streamlining the work of assurance and audit practitioners, specifically in cybersecurity, privacy, and financial audits. Put simply, we build software for the people who enable trust between businesses.

We’re based in San Francisco, CA, but built as a remote-first company that enables you to do your best work from anywhere. We’re backed by top investors, including Growth Equity at Goldman Sachs Alternatives, Bessemer Venture Partners, 8VC, Floodgate, Y Combinator, DNX Ventures, Global Founders Capital, Justin Kan, Elad Gil, and more.

We value diversity—in backgrounds and experiences. We need people from all backgrounds and walks of life to help build the future of audit and advisory. Fieldguide’s team is inclusive, driven, humble, and supportive. We are deliberate and self-reflective about the kind of team and culture we are building, seeking teammates who are not only strong in their own aptitudes, but who also care deeply about supporting each other’s growth.

As an early-stage startup employee, you’ll have the opportunity to help build the future of business trust. We make audit practitioners’ lives easier by consolidating up to 50% of their work and improving work-life balance. If you share our values and enthusiasm for building a great culture and product, you’ll find a home at Fieldguide.

What You’ll Own

-

Agent infrastructure and tooling: Build and maintain the internal platform that makes agentic workflows reliable and easy to adopt for team members—MCP integrations, prompt/skill libraries, shared configurations, knowledge systems, and tooling that connects agents to our codebase, docs, and internal services.

-

Developer experience for AI workflows: Make the right way to use AI the easy way for all team members. Build onboarding and documentation, define clear paths for common workflows (planning, testing, ticket creation, code review, production support), and create feedback loops that show what’s working and what isn’t.

-

Measurement and attribution: Build instrumentation to track efficiency metrics, agent effectiveness, and team productivity.

-

Experimentation and evaluation: The AI tooling landscape changes quickly. Run structured trials of new tools, synthesize learnings, and maintain a living point of view the team can follow.

-

Enablement and culture: Run trainings, office hours, internal demos, and coaching that raise the floor across the org—so every engineer can be AI-native from day one.

What You Bring

Must-haves

-

Excellent engineer first: You ship reliable internal tools, build integrations, and debug production systems. You love building things.

-

Deep hands-on experience with AI coding tools: You’ve used Claude Code, Cursor, Codex, and more in real engineering work—not toy projects. You have strong opinions on what works and what doesn’t.