Applied AI Engineer

Plotwell Inc.; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Plotwell Inc. is seeking an applied software role focused on chart selection and story extraction from revenue dashboards, owning the prompts, JSON contract, and ensuring the model's integrity.

You will build evaluation sets, keep the model lightweight and grounded, and collaborate with engineering to drop ungrounded numbers while delivering measurable improvements.

Qualifications

• Four or more years shipping software products.
• Experience with language-model work in production settings.
• Ability to evaluate changes with measurable impact.
• Desire to keep the model as the smallest, well-scaffolded part of the system.

Responsibilities

• Own the prompts and the JSON contract for chart selection and takeaways.
• Build the evaluation set: real spreadsheets with known dashboards, run on changes.
• Collaborate with engineering to ensure grounding checks drop ungrounded numbers.
• Evaluate and iterate with data-driven results rather than vibes.

Skills

Shipping software

Language-model work

Job description

When Plotwell looks at a file and decides the story is revenue by month with churn under it, that judgement comes from a model and a lot of careful scaffolding. You own that.

This is an applied role with a product output. You decide what good chart selection looks like, keep the model honest, and make the routing layer earn its keep.

What you would own

• Own the prompts and the JSON contract for chart selection and takeaways.
• Build the evaluation set: real spreadsheets with known good dashboards, run on every change.
• Keep Plotwell model-agnostic, and measure when a cheaper model is good enough.
• Work with engineering on the grounding check that drops ungrounded numbers.

What we are looking for

• Four or more years shipping software, with real language-model work behind you.
• You evaluate rather than vibe-check, and you can prove a change helped.
• You are comfortable owning a fuzzy problem with a measurable output.
• You want the model to be the smallest, best-scaffolded part of the system.

How hiring runs

A thirty minute call with a founder, then a paid work session on a real problem from our backlog, three to four hours, then conversations with two people you would work alongside. Four steps, usually inside two weeks, and we tell you where you stand at every one.