Fieldguide is building AI agents for the most complex audit and advisory workflows. We're a San Francisco-based Vertical AI company building in a $100B+ market undergoing rapid transformation. Over 50 of the top 100 accounting and consulting firms trust us to power their most mission-critical work.
We're backed by Bessemer Venture Partners, 8VC, Floodgate, Y Combinator, Elad Gil, and other top-tier investors.
As an
AI Engineer
, you'll design and build the intelligence layer of Fieldguide, the agentic workflows, architectures, and evaluation systems that power enterprise-grade agents. This role sits at the intersection of product engineering, applied AI, and production systems.
We're hiring across all levels. We'll calibrate seniority during interviews based on your background and what you're looking to own. This role is for engineers who value in-person collaboration at our San Francisco, CA office.
What You'll Own
Building and shipping AI agents
Design, build, and ship agentic systems that automate and augment complex audit workflows
Translate customer problems into concrete agent behaviors and workflows
Integrate and orchestrate LLMs, tools, retrieval systems, and logic into cohesive, reliable agent experiences
Own agents in production, including performance and observability
AI-native engineering execution
Use AI as core leverage in how you design, build, test, and iterate
Prototype quickly to resolve uncertainty, then harden systems for enterprise-grade reliability
Build evaluations, feedback mechanisms, and guardrails so agents improve over time
Design prompts, retrieval pipelines, and agent orchestration systems that perform reliably at scale
Product judgment and customer impact
Make tradeoffs about what to build, what to cut, and what not to build at all
Partner closely with Product and Design to define agent capabilities that drive real customer outcomes
Stay deeply connected to how customers actually use agents and optimize for the highest impact problems
Identify the highest-leverage capability gaps and unblock them without waiting for direction
Ownership of large product areas
Take full ownership of large product areas rather than executing on narrow tasks
Identify bottlenecks and unblock progress without waiting for direction
Increase team velocity by building reusable abstractions, tools, and patterns for agent development
Who You Are
You are a strong software engineer who has built your skills for an AI-native world. The following operating principles should resonate with you:
Bias to building:
You move fast and resolve uncertainty by shipping software
AI-native instincts:
You treat LLMs, agents, and automation as fundamental building blocks and parts of the craft of engineering
Strong product judgment:
You can decide what matters and why, without waiting for guidance, not just how to implement it
Learning velocity:
You move fast, learn from feedback, and adjust based on data
Grounded optimism:
You improve what is broken today and are energized by what becomes possible next
End-to-end thinker:
You understand how systems behave in production and own outcomes
Experience
We care more about capability and trajectory than years on a resume, but most strong candidates will have:
Multiple years of experience shipping production software in complex, real-world systems
Experience with TypeScript, React, Python, and Postgres
Built and deployed LLM-powered features serving production traffic
Designed retrieval pipelines and agent orchestration systems
Implemented evaluation frameworks for model outputs and agent behaviors
Worked with vector databases, embedding models, and RAG architectures
Hands-on experience with modern LLM APIs (OpenAI, Gemini, Anthropic, etc.) and agent frameworks
Comfort operating in ambiguity and taking responsibility for outcomes
Deep empathy for professional-grade, mission-critical software (experience with audit and accounting workflows are not required)
What Should Excite You
Agent reliability at enterprise scale:
Building systems that professionals depend on
Balancing automation with human oversight:
Knowing when to automate and when to surface decisions to experts
Building evaluation systems when ground truth is nuanced:
Audits require judgment, so structuring data in ways to get feedback is essential
Explaining AI decisions:
Making all forms of AI outputs and agent reasoning transparent and trustworthy
Operating in a complex industry:
Understanding compliance constraints and enterprise rigor while also moving fast
Applied engineering
where you ship agent experiences customers depend on daily
Benefits
Competitive compensation packages with equity ownership
Comprehensive health and wellness benefits
Flexible time off and work schedules
Technology reimbursements
401(k) plan
Twice-yearly in-person offsites across the U.S.
Our Values
Fearless
— Inspire & break down seemingly impossible walls
Fast
— Launch fast with excellence; iterate to perfection