Partner closely with engineering, product, and design teams to translate real-world SOX testing processes into scalable product capabilities.
Co-develop AI agents with AI engineers to execute detailed SOX testing by translating SOX testing methodology into specific guidance, decision rules, and examples.
Work hands-on with AI agents: write and refine prompts, run controls and evidence through testing workflows, evaluate outputs, and document failure modes.
Analyze risk and control matrices and test plans to identify opportunities for improved agentic testing.
Develop stress-test scenarios, review and assess AI agent performance, and create detailed error analyses and evaluation criteria.
Showing 1 of 26 positions
About Fieldguide
Fieldguide pioneers the future of audit and advisory, building an AI-native platform that transforms how Assurance and Advisory firms operate. You will join a company backed by $125 million in funding, including top investors like Goldman Sachs Alternatives, Bessemer Venture Partners, and Y Combinator. Their platform automates and streamlines complex workflows, reducing manual effort by up to 50% for practitioners. Fieldguide is trusted by half of the Top 100 U.S. accounting firms, including Big Four members, to increase margins and strengthen client relationships. They empower these firms to provide essential trust for global commerce and capital markets.
How We Work
Fieldguide operates as a remote-first company, enabling you to work effectively from anywhere. While based in San Francisco, their team spans multiple time zones, fostering a diverse and inclusive environment. They champion proactive communication to ensure smooth collaboration and clear expectations. You will find a team that is inclusive, driven, humble, and supportive, focused on mutual growth. Decisions happen in open discussions, with a strong emphasis on trust and collaboration across functions.
Engineering at Fieldguide
Fieldguide is building advanced AI agents for the most complex audit and advisory workflows, operating at the intersection of ML engineering, observability, and quality assurance. Engineers design and build unified evaluation platforms that ensure AI agents perform reliably at enterprise scale. They work with modern web technologies like TypeScript, React, Node.js, Python, and GraphQL. The team leverages relational databases such as PostgreSQL and cloud infrastructure, primarily AWS. You will engage with agentic AI, integrate with tools like LangSmith and LangGraph, and implement SLO-driven engineering practices. They focus on architecting scalable, fault-tolerant distributed systems that shape the future of business trust.
Why Join Us
Shape the future of business trust with an AI-native platform disrupting a $100B+ market.
Work in a remote-first environment with flexible schedules and meaningful ownership.
Solve complex engineering challenges using cutting-edge AI and distributed systems technologies.
Contribute to a diverse, inclusive, and supportive team focused on continuous growth.
Impact practitioner lives by reducing manual work and improving work-life balance.
Benefits & Perks
Competitive compensation packages with meaningful equity ownership