Software Engineer, Agents (Internal Audit)

Fieldguide•San Francisco, CA

8d•$170,000 - $300,000•Hybrid

About The Position

Fieldguide is building software for assurance and audit practitioners, focusing on cybersecurity, privacy, and financial audits. The company aims to establish a new state of trust in global commerce and capital markets by automating and streamlining audit work. Backed by prominent investors and trusted by many top accounting and consulting firms, Fieldguide is seeking a product-focused Software Engineer to join a new team on a significant company initiative. This role involves owning agent quality, shipping agents that perform audit tasks, and collaborating with practitioners. The position is open to various experience levels, with responsibilities and scope to be determined during the interview process.

Requirements

Shipped LLM-backed product features to production against real users.
Applied AI skillset: evals, error analysis, and model-selection decisions that were owned and can be explained.
Comfortable full-stack, with sufficient backend depth for agent orchestration.
Autonomy working from an ambiguous spec.
Collaborative approach working across PM, design, and domain experts.
Strong instincts for human-in-the-loop design.
Team player across the organization, working daily with PM, design, domain experts, and customer-facing teams.
Ability to write reviewable, tested, and instrumented code.
Ability to internalize a hard domain quickly.
Experience with Python, TypeScript, React, Postgres, Hasura, GraphQL (Nice-to-have).
Experience with Temporal or comparable durable-execution / workflow orchestration (Nice-to-have).
Hands-on eval experience (e.g., Langfuse, Braintrust, LangSmith, Arize Phoenix) (Nice-to-have).
Experience with structured-output work, including schema contracts and generating artifacts from model output (Nice-to-have).
Startup experience, as a founder or early engineer (Nice-to-have).
A 0→1 track record: initiated projects where no scaffolding existed (Nice-to-have).
Experience working directly with customers and comfort being present when they use built products (Nice-to-have).
Background in internal audit, SOX, accounting, or another regulated domain (Nice-to-have).
Experience with document processing, including PDF and Excel manipulation and annotation (Nice-to-have).

Nice To Haves

Python, TypeScript, React, Postgres, Hasura, GraphQL
Temporal or comparable durable-execution / workflow orchestration
Hands-on eval experience (Langfuse, Braintrust, LangSmith, Arize Phoenix, or comparable)
Structured-output work including schema contracts, generating real artifacts from model output
Startup experience, as a founder or as an early engineer
A 0→1 track record: things you started where no scaffolding existed
Experience working directly with customers, and comfort being in the room when they use what you built
Background in internal audit, SOX, accounting, or another regulated domain
Document processing, including PDF and Excel manipulation and annotation

Responsibilities

Make agent judgment repeatable by running error analysis on testing data and implementing fixes.
Manage tradeoffs between quality, latency, and cost in multi-phase runs.
Build structured-output pipelines to convert model output into audit artifacts.
Transform ambiguous problem statements into actionable plans, shipped features, and clear documentation of scope decisions.
Collaborate directly with an embedded subject matter expert and design-partner firms, iterating on agent changes rapidly.
Expand agent coverage to new controls and areas within internal audit.
Own a major agent area end-to-end, including reasoning about controls and generating reviewer-signed artifacts (Senior level).
Establish and lead the evals and error-analysis practice for agent work, determining when to ship changes or roll back (Senior level).
Collaborate with PMs and designers on roadmaps and architectural tradeoffs, defining agent vs. auditor decision points (Senior level).
Manage complex model and orchestration decisions for multi-phase runs (Senior level).
Mentor other engineers and improve 0→1 execution and eval rigor (Senior level).
Drive agent initiatives beyond Internal Audit, influencing agent development across Fieldguide (Staff level).
Set and champion engineering standards for agent reliability, reproducibility, and defensibility (Staff level).
Partner with leadership to define long-term technical strategy for agentic audit work (Staff level).
Serve as a trusted advisor to leaders across Engineering, Product, and Design (Staff level).
Represent Fieldguide externally through writing, speaking, and open-source contributions (Staff level).