Senior AI Engineer

Fieldguide•San Francisco, CA

10d•Remote

About The Position

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. As a Senior AI Engineer, you'll own meaningful product areas end-to-end—designing agentic architectures, building evaluation systems, and shipping agents that professionals trust with mission-critical work. This role is for engineers who have shipped LLM-powered features in production and are ready to take the lead on complex systems while mentoring those around them.

Requirements

Strong software engineer who’s built their skills for an AI-native world
Bias to building: You move fast and resolve uncertainty by shipping
AI-native instincts: You treat LLMs, agents, and automation as core building blocks
Strong product judgment: You decide what matters and why—not just how to implement it
Learning velocity: You learn quickly from feedback and adjust based on data
Grounded optimism: You improve what's broken today and push toward what's possible next
End-to-end ownership: You understand production systems and own outcomes
3–6+ years shipping production software in complex, real-world systems
Strong command of TypeScript, Python, and Postgres
Shipped LLM-powered features serving real production traffic
Built retrieval pipelines and agent orchestration systems
Implemented evaluation frameworks for model outputs and agent behavior
Worked with vector databases, embedding models, and RAG architectures
Hands-on experience with modern LLM APIs (OpenAI, Gemini, Anthropic) and agent frameworks
Comfortable operating in ambiguity and taking responsibility for outcomes

Responsibilities

Design and build agentic systems that automate complex audit workflows end-to-end
Translate customer problems into concrete agent behaviors and orchestration logic
Orchestrate LLMs, tools, retrieval, and business logic into reliable, production-grade agent experiences
Own agents across their lifecycle: delivery, reliability, performance, and observability
Use AI to accelerate design, build, test, and iteration cycles
Prototype quickly, then harden systems for enterprise-grade reliability
Build evaluation frameworks, feedback loops, and guardrails to improve agents over time
Design prompts, retrieval pipelines, and orchestration logic that perform at scale
Make clear trade-offs on what to build, cut, or skip based on customer value
Partner with Product and Design to define capabilities that deliver real outcomes
Stay close to customer workflows and optimize for highest-impact problems
Identify capability gaps and unblock team progress proactively
Raise the quality bar through code review, design feedback, and pairing
Create reusable abstractions, patterns, and tooling that increase team velocity
Share learnings across the team and establish engineering best practices