Fieldguide
Software Engineer, Agents (Foundation Agents)
About this role
Join Fieldguide's Foundation Agents team to build and improve long-horizon AI agents that perform real-world work in audit and compliance. You'll focus on agent knowledge infrastructure, evaluation systems, error analysis, and backend reliability to power mission-critical AI products for top accounting and consulting firms.
What you'll do
- Develop and maintain agent knowledge and evaluation infrastructure for production long-horizon agents
- Build next-generation agents addressing complex customer use cases in audit and compliance
- Conduct error analysis on agent behavior and translate findings into quality improvements
- Design backend systems for agent execution, evaluation, and monitoring at scale
- Partner with senior engineers to execute reliability and quality roadmap
- Troubleshoot and improve agent performance in production environments
What they're looking for
- AI/ML product development (not just LLM API calls)
- Evaluation frameworks and error analysis
- Backend engineering and system design
- Python or similar backend languages
- Platform engineering (nice-to-have)
- Distributed systems (nice-to-have)
- Frontend development (nice-to-have)
- Debugging and observability practices
Benefits
- Competitive compensation with equity
- Comprehensive health and wellness benefits
- Flexible time off and remote work options
- Technology reimbursements
- 401(k) plan
- Twice-yearly in-person team offsites
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Fieldguide
Fieldguide builds audit and advisory software that modernizes trust and compliance for global commerce, with a focus on cybersecurity and privacy. The company is hiring Software Engineers, AI Engineers, and Production Support Engineers across all levels to design impactful features, develop agentic AI workflows, and drive system reliability.
- Website
- fieldguide.com
Likely interview questions
- Walk us through a production AI product you've built end-to-end. What made it challenging, and how did you measure quality?
- Describe a time an AI system failed in unexpected ways. How did you analyze the root cause and prevent recurrence?