SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Fieldguide is automating and streamlining assurance and audit work for global commerce and capital markets, with a focus on cybersecurity, privacy, and financial audits. The company is backed by Goldman Sachs Alternatives, Bessemer Venture Partners, 8VC, Floodgate, and Y Combinator, and is trusted by over 50 of the top 100 accounting and consulting firms.
The Foundation Agents team stewards long-horizon agents powering the Fieldguide AI platform, working at the frontier of AI product development. You will own the infrastructure and execution of agents that perform real, sustained work in production environments.
Key responsibilities:
- Build and maintain agent knowledge and evaluation infrastructure for Fieldguide's long-horizon agents
- Develop next-generation agents solving increasingly complex customer use cases
- Perform error analysis on agent behavior and translate findings into concrete quality improvements
- Build backend systems supporting agent execution, evaluation, and monitoring
- Partner with senior engineers to execute the platform's reliability and quality roadmap
You will work on long-horizon agents that do real work, not one-shot demos. Evaluation and error analysis are core to how the team improves quality. Your work shapes the reliability and quality of every agent built on the platform, tackling frontier problems in agent reliability without established playbooks.
REQUIREMENTS:
Must-have:
- Hands-on experience building AI products
- Working knowledge of evals and error analysis
- Backend engineering experience
Nice-to-have:
- Platform engineering skills
- Frontend experience
- Distributed systems experience
