Senior/Staff Software Engineer, Agents (US)
Fieldguide • Financial District, San Francisco, CA
Company
Fieldguide
Annual salary
$220k – $315k/yr
Location
Financial District, San Francisco, CA
Listed
26d ago
- Experience:
- 6 to 15 years
- Workplace:
- 3 days in-office in Financial District, San Francisco (575 Market St). This is the team average with no set days; some people come in 5 days.
- Equity:
- Competitive equity
Open to people who live in the US, Canada or the UK
We can only put candidates forward for this role from those three countries for now. See the contract AI training jobs open in more countries.
Hybrid in Financial District, San Francisco, CA.
Send us your LinkedIn and CV. If your experience fits, we'll introduce you to the recruiter filling this role.
Apply for a referral →The recruiter emails you before anything happens and may suggest other jobs that suit you better.
About this role
The Foundation Agents team stewards the long-horizon agents powering the Fieldguide AI platform. We work at the frontier of AI product development: agent knowledge, evaluations, and improving quality and reliability at scale. As a Senior Software Engineer, Agents, you’ll take ownership of how the team measures and improves agent quality, and help drive the platform forward.
What you'll do
- Evals strategy and error-analysis practice, shaping how the team measures and improves agent quality
- Design and build agent knowledge and evaluation infrastructure for Fieldguide’s long-horizon agents
- Lead error analysis on agent behavior, turning findings into concrete platform-level reliability improvements
- Build and harden backend systems that support agent execution, evaluation, and monitoring at scale
- Drive the AI platform’s reliability and quality roadmap forward, working closely with the broader AI team
- Mentor engineers on the team, raising the bar on eval rigor and error-analysis practice
What you need
- You’ve built AI products end-to-end, with real ownership over agent quality outcomes
- You think in evals and error analysis as a discipline; you dig into why an agent failed and fix the systemic cause
- You’re strong in the backend and comfortable owning platform-level systems
- You’re motivated by long-horizon agents that do real work in production
- You multiply the people around you, not just your own output
What Should Excite You
Long-horizon agents: Working on agents that do real, sustained work
Evaluation as a craft: Evals and error analysis are core to how this team improves quality, not an afterthought
Platform-level impact: Your work shapes the reliability and quality of every agent built on top of it
Frontier problems: You’re working on open problems in agent reliability that don’t have established playbooks yet
Common questions
How do I apply for the Senior/Staff Software Engineer, Agents (US) role at Fieldguide? +
Use the Apply for a referral button on this page to send us your LinkedIn and CV. If your experience fits, we'll introduce you to the recruiter filling this role. They'll email you to check you're interested, then put you forward for this job or others that suit you better. It's free.
What does this Fieldguide role pay? +
The listing gives $220k – $315k/yr.
Is this role remote? +
The listing gives the location as Financial District, San Francisco, CA. 3 days in-office in Financial District, San Francisco (575 Market St). This is the team average with no set days; some people come in 5 days.
Software Engineer interview prep
Questions Software Engineer interviewers often ask. They aren't taken from this listing.
How do you approach designing a system when the requirements are still likely to change?
I design around the parts of the problem I'm confident are stable, like the core data model, and keep the parts most likely to change, like specific business rules, isolated behind clear interfaces. Over-engineering flexibility everywhere just adds complexity to parts of the system that were never going to change.
What's your process for debugging an issue that only reproduces in production, not locally?
I add targeted logging around the suspected area and compare production data or configuration against my local setup, since an issue that's environment-specific usually traces back to a real difference between the two rather than a fundamentally different bug. I avoid making speculative changes without first confirming where the divergence is.
How do you decide when a piece of code needs a test versus when it's low-risk enough to skip?
I prioritize tests for logic with real business consequences if it breaks, or code that's likely to be touched again later by someone unfamiliar with it. Simple, rarely-changed glue code gets less coverage, since the cost of a thorough test there often exceeds the risk it's protecting against.
How do you evaluate a proposed technical solution's trade-offs, like performance versus maintainability?
I start from the actual constraint that matters for this specific system, whether that's genuinely performance-critical or whether maintainability is the bigger long-term cost, rather than defaulting to whichever trade-off I personally prefer. Optimizing for performance the system doesn't need just adds complexity nobody benefits from.
Related roles
Browse all referral roles
Salaried roles at startups, AI companies and established businesses, all filled by referral. One application covers every role.
See all referral roles →