AI Engineer
External
Fieldguide · San Francisco, CAPrepare for this interview
EliteAI-generated questions, company research, and talking points tailored to this role
About the role
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. We build software for the people who enable trust between businesses. We're based in San Francisco, CA, and built remote-first. We're backed by Goldman Sachs Alternatives, Bessemer Venture Partners, 8VC, Floodgate, Y Combinator, and more. Over 50 of the top 100 accounting and consulting firms trust Fieldguide to power mission-critical work. Fieldguide is building AI agents for the most complex audit and advisory workflows. We're a San Francisco-based vertical AI company operating in a $100B+ market undergoing rapid transformation. Over 50 of the top 100 accounting and consulting firms trust Fieldguide to power mission-critical work. As an AI Engineer, you'll build Fieldguide's intelligence layer-agentic workflows, architectures, and evaluation systems that power enterprise-grade agents. You'll operate at the intersection of product engineering, applied AI, and production systems.
Responsibilities
- Build and Ship AI Agents
- Implement agentic workflows that automate complex audit tasks
- Turn customer problems into discrete, testable agent behaviors
- Integrate LLMs, tools, and retrieval logic into reliable agent experiences
- Monitor and maintain agents in production with a focus on reliability and performance
- Execute with AI-Native Leverage
- Use AI tooling to accelerate how you design, build, and test features
- Prototype quickly and harden systems for enterprise reliability
- Build evaluations and feedback loops to improve agent outputs
- Write prompts and retrieval pipelines that perform at scale
- Contribute to Product Impact
- Work closely with senior engineers and product to scope and deliver features
- Translate customer workflows into clear engineering requirements
- Identify and surface capability gaps to improve team velocity
Requirements
- You're a strong software engineer who's built your skills for an AI-native world. These principles resonate with you:
- Bias to building: You move fast and resolve uncertainty by shipping
- AI-native instincts: You're excited to use LLMs, agents, and automation as core tools
- Curiosity and learning velocity: You ramp quickly on new problems and technology
- Collaborative: You communicate proactively and seek feedback often
- Attention to detail: You care about quality in code and customer-facing outputs
- We care more about capability and trajectory than years on a resume, but most strong candidates have:
- 1-3 years shipping production software in real-world systems
- Proficiency in TypeScript and/or Python
- Some exposure to LLM APIs (OpenAI, Anthropic, Gemini) or AI tooling
- Familiarity with retrieval pipelines, RAG concepts, or vector databases is a plus
- Experience with React and Postgres is helpful but not required
- Comfortable working in ambiguity with direction from senior engineers
- What Should Excite You
- Enterprise-grade reliability: Building systems professionals depend on
- Human-in-the-loop design: Knowing when to automate vs. when to surface decisions
- Nuanced evaluation: Audits require judgment, so feedback structures matter
- Explainability: Making AI outputs and reasoning transparent and trustworthy
- Complex domains: Navigating compliance and enterprise rigor while moving fast
- Shipping daily value: Delivering agent experiences customers use every day
Benefits
Your Match
How well this role fits your profile.
Company Intel
What employees say
Worked at fieldguide? Share your experience