FieldGuide
Software Engineer, Agents (Internal Audit)
$170K–$300K
San Francisco, CA · Hybrid · Full-time · Posted Sep 17, 2026
- Experience
- No years specified; hiring across all levels, with scope calibrated during interviews.
About the job
Build and ship production AI agents that perform internal audit work, improving their quality and converting model output into reviewable audit artifacts.
What you'll do
- Analyze agent errors and testing data to implement quality improvements and balance quality, latency, and cost.
- Build structured-output pipelines and expand agent coverage to new controls and internal audit areas.
- Work with subject matter experts and design-partner firms to turn feedback into shipped product changes.
What they ask for
- Have shipped LLM-backed product features to production for real users.
- Have applied AI experience with evals, error analysis, and model-selection decisions you owned and can explain.
- Be comfortable working full-stack, with sufficient backend depth for agent orchestration.
- Work autonomously with ambiguity and collaborate across product, design, and domain experts.
Nice to have
- Experience with Python, TypeScript, React, Postgres, Hasura, GraphQL, or durable workflow orchestration.
- Experience with evaluation tools, structured outputs, startups, customers, regulated domains, or document processing.
Pay
$170K – $300K USD base salary
Tools
Python, TypeScript, React, Postgres, Hasura, GraphQL, Temporal, Langfuse
AI focus
Develop and evaluate production LLM agents for internal audit, including model selection, orchestration, error analysis, structured outputs, and human-in-the-loop workflows.
Model-written summary · the original posting is authoritative