Staff AI Engineer

Fieldguide•San Francisco, CA

6h•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. About the Role Fieldguide is building AI agents for the most complex audit and advisory workflows. As a Staff AI Engineer, you'll shape the technical direction of our intelligence layer—defining the architecture, standards, and roadmap that enable Fieldguide to build the most reliable AI agents in the enterprise. This role is for experienced engineers who combine deep technical judgment with strong product instincts and organizational influence. You'll operate across the engineering organization to drive impact that compounds over time.

Requirements

8+ years shipping production software, with 3+ years leading complex AI/ML systems
Deep expertise in TypeScript, Python, and distributed system design
Proven track record shipping LLM-powered products at enterprise scale
Experience defining evaluation infrastructure and reliability standards for AI systems
Mastery of retrieval architectures, RAG, vector databases, and embedding pipelines
Hands-on with cutting-edge LLM APIs and agent frameworks (OpenAI, Anthropic, Gemini, LangGraph, etc.)
Experience influencing technical direction across multiple teams or product areas
Track record mentoring senior engineers and growing engineering culture

Responsibilities

Define and Drive Technical Direction
Set the architectural direction for Fieldguide's agentic systems and intelligence layer
Identify and resolve systemic gaps that limit reliability, scalability, or product velocity
Make high-leverage technical bets and drive them to completion across the organization
Establish evaluation standards, observability infrastructure, and reliability frameworks at scale
Build and Ship High-Impact Systems
Own the most complex, cross-cutting product areas end-to-end
Design agent orchestration and retrieval systems that handle enterprise-grade complexity
Lead the evolution of Fieldguide's LLM infrastructure: models, prompts, guardrails, and feedback loops
Prototype, validate, and harden novel approaches before sharing with the broader team
Drive Organizational Leverage
Partner with Engineering leadership, Product, and Design to shape the AI roadmap
Create reusable platforms, patterns, and tooling that multiply team velocity across the org
Identify and develop the next generation of senior engineers
Translate long-term product vision into concrete technical strategies
Represent and Advance the Field
Stay at the frontier of LLM and agent research; rapidly evaluate and adopt what matters
Build internal knowledge and shared understanding of AI system design
Contribute to Fieldguide's reputation as a technical leader in vertical AI