Senior Software Engineer, Applied AI

TLDR

2d•$250,000 - $300,000•Remote

About The Position

TLDR's Applied AI program runs on one thesis: every process at the company should get better automatically as model capabilities improve. An LLM sits in the loop on every workflow, and the work of the people around it shifts from clicking and typing toward writing specs and evals and deciding what good looks like.

Requirements

5+ years experience including 2+ years building products and systems with LLMs, with at least one agent you took to production and still own.
You code fluently with AI tools like Claude Code or Codex.
You write evals as part of building, not after. You can say how you defined good, what you measured, and what you changed as a result.
You ship end to end and don't wait for someone to spec the small stuff.
You have product judgment: you can say what you chose not to build, and why.
You're comfortable in a domain where settled practice doesn't exist yet.
You can sit with non-engineering stakeholders and find where an LLM belongs in their process.
The way you build has changed as models have gotten better, and you treat capability improvement as a design input.
You want surface area across nearly every function of a profitable, bootstrapped company, with no legacy systems to fight, direct CEO access, and an unlimited token budget.

Responsibilities

Own the build out of new agents, skills, and platform capability for teams across TLDR.
Build and deploy agents end to end, from design through implementation, evals, and rollout to internal users.
Write the evals and specs that define what good looks like, so workflow quality is measurable rather than anecdotal.
Partner with our Applied AI PM on what to build, and make the smaller product calls independently.
Work directly with stakeholders in sales, revenue ops, editorial, and people ops to find where an LLM belongs in their process.