You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Petual

Software Engineer

  • Office

Salary

Not stated

Similar roles pay $160K - 240K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company builds an AI control tester for enterprises. Its agents check whether a company's financial, operational, and technology controls work, and link each conclusion back to its source.

Accuracy matters more than speed here. External auditors repeat the work, so the agents must be as precise on the 400th sample as on the first, and when an agent cannot back up a conclusion it must say so instead of guessing.

The company is backed by Andreessen Horowitz. The team has people from Stripe, Retool, and Lyft. Public companies already run their SOX programs on the product.

The core challenge is not getting an agent to test one control. It is knowing whether it was right across hundreds of controls, for customers with different methodologies, where the reference answer is a senior auditor's judgment rather than a labeled dataset. Building the harness and evaluation that make this workable is the heart of the role, and you would own it.

Responsibilities

  • Own the agent harness: the workflows, checkpoints, and evaluation that keep long-running agents reliable over hours of testing.
  • Design and own the backend services and APIs that move evidence from ingestion through analysis to output auditors can rely on.
  • Build integrations with the systems customers store evidence in, such as cloud infrastructure, identity providers, ticketing systems, and ERPs.
  • Design data models and system architecture that keep working as the customer base and control volume grow.
  • Write code and design systems with security and data integrity as first priorities, since customers share sensitive evidence.
  • Work directly with customers to build the features that matter most to the people doing the testing.

Requirements

  • You have built on LLMs or agentic systems, including harnesses, long-running agents, evals, or workflows that hold up against messy real-world input.
  • You have built enterprise SaaS products that handle sensitive customer data.
  • You are strong across the stack: solid backend skills in APIs, data modeling, and distributed systems, plus enough frontend ability to ship a feature end to end.
  • You have worked with AWS, Kubernetes, and infrastructure as code.
  • You have worked in fintech, audit, governance, risk, compliance, or another regulated field.
  • You have taken high ownership at an early- or growth-stage startup, shaping the product and processes as well as the code.

Where you’d work

From the office

The office

About the company

Petual

Office in San Francisco, United States

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 18 checks run
  • 1 red flag

Still hiring?

12 checks

1 red flag

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details8 facts · Role, Location, Compensation
Tech stack
  • AWS
  • Kubernetes
  • LLMs
Specialty
Backend
Region
United States
Pay period
Annual
Show 4 more factsShow less

Role

Category
Development
Specialty
Backend
Tech stack
  • AWS
  • Kubernetes
  • LLMs

Location

Work model
Office
Region
United States
Office
  • San Francisco, United States

Compensation

Salary
Salary by agreement
Pay period
Annual

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason