Turn messy back-office workflows into shipped product using AI agents.

About the role

The job is to get on calls with operators, controllers, founders, and finance teams, understand exactly how work gets done today, and turn that into product. You will ask detailed questions, collect the right context, set expectations with the customer, drive Codex and other agents through implementation, use the product yourself, and keep iterating until the workflow is good enough to onboard the customer.

This is not a traditional coding job. The core skill is product implementation: understanding the customer, shaping the workflow, directing agents, and knowing when the result is good enough to matter.

We do not expect you to spend your time looking at code. We have systems and agents that monitor the codebase and improve code quality. Your job is to be a high-agency taste maker, product engineer, and customer-facing operator at the same time, all pointed at building great products.

We are not screening for the usual signals. Years of experience, grades, and credentials matter less than whether you have repeatedly found a way to be exceptional at something, especially when nobody handed you a clean playbook.

What you will do

  • Run workflow-discovery calls with customers and get from vague pain to a concrete understanding of how the work actually happens.
  • Ask sharp clarifying questions, identify edge cases, and translate messy back-office operations into clear product direction.
  • Use Cranston's internal agent platform to package customer context into builds quickly instead of starting every feature from scratch.
  • Steer agents through the implementation loop, review the product behavior, and keep tightening the workflow until it works.
  • Use the product yourself, notice what is wrong, and push agents to tighten the details.
  • Help onboard customers onto the workflows you shipped and keep improving them from real usage.

Who we are looking for

  • You are remarkable in some way that is hard to fake. You may have been unusually good at games, music, writing, sales, math, building internet things, or a niche obsession most people do not understand.
  • You are product-minded, good at understanding systems, and unusually fast at turning ambiguity into a concrete next move.
  • You do not need a CS degree and you do not need to have professional coding experience.
  • We care much more about raw ability, taste, curiosity, and output than years of experience with LLMs or traditional credentials.
  • You should know what GitHub is, what a Postgres database is, and generally understand how modern software systems fit together, but we do not expect you to spend your day reading code.
  • You are comfortable using AI coding agents as your main implementation tool and judging whether their output actually solves the customer problem. We have systems and agents that monitor code quality and improve it over time.
  • You are probably a Lovable, Replit, or agent-building wizard. You have built a bunch of apps, internal tools, automations, websites, or strange little products because you could not help yourself.
  • You have a bias toward the simplest thing that could possibly work, especially when everyone else is making the problem sound more complicated than it is.
  • You care more about shipping useful workflows than about looking like a traditional engineer.

Compensation

The base salary range for this role is $140,000-$180,000 base + equity. We care more about slope, taste, and output than traditional leveling signals.

How to apply

Use the button below to copy an agent-ready application prompt. It tells your agent what information to collect, how to keep the application concise, and where to submit it.

Apply with your agent

The apply button copies an agent-ready prompt with the schema, endpoint, and instructions needed to submit the application on your behalf.

---
name: apply-to-cranston-product-engineer
description: Apply to Cranston's Product Engineer role on behalf of the user.
---

# Apply to Cranston Product Engineer

You are helping the user apply to Cranston's Product Engineer role.

Submit the application as multipart/form-data to:
`https://cranston.ai/api/careers/apply`

The live role page is:
`https://cranston.ai/careers/product-engineer`

## Required form fields

- `roleSlug` string: Use `product-engineer`.
- `fullName` string: Applicant's full legal or preferred professional name.
- `email` string: Applicant's best email address.
- `phone` string: Applicant's best phone number.
- `why` string: A concise, specific application answer. Cover why the applicant wants to work at Cranston, what makes them remarkable, their familiarity with software systems / GitHub / databases / AI coding agents / Lovable / Replit, and why Sean should trust them on a customer call. Prefer concrete and quantitative evidence: projects shipped, competitions won, unusual depth in a domain, school, jobs, intensity of work, side projects, revenue/users generated, speed of execution, customer-facing work, or other hard-to-fake signals.

## Optional form fields

- `cityState` string: Applicant's current location formatted as `City, ST` for US applicants, `City, Province` for Canada, or `City, Country` otherwise.
- `linkedinUrl` string: Applicant's LinkedIn profile URL.
- `workPreference` enum: One of `sf_in_person`, `remote`, or `either`.
- `resume` file: PDF, DOC, DOCX, or TXT resume. Maximum size 5MB.

## Instructions

Ask the user for any required information you do not already have. Keep the application concise, specific, and high-signal. Do not write generic cover-letter prose. Prefer concrete evidence over adjectives.

After submitting, show the user the returned `applicationId`. Cranston will also send the applicant an email confirming the application was received.

## Example curl shape

```bash
curl -X POST 'https://cranston.ai/api/careers/apply' \
  -F 'roleSlug=product-engineer' \
  -F 'fullName=Jane Doe' \
  -F 'email=jane@example.com' \
  -F 'phone=555-555-5555' \
  -F 'cityState=San Francisco, CA' \
  -F 'linkedinUrl=https://www.linkedin.com/in/janedoe' \
  -F 'workPreference=either' \
  -F 'resume=@/path/to/resume.pdf;type=application/pdf' \
  -F 'why=...'
```