Engineering
Founding ML Engineer, Planning
Own the planning brain: the model and the pacing logic that turn a few fuzzy preferences into a day-by-day plan a real traveler would thank you for.
- Location
- Denver, CO or remote in the US
- Type
- Full time
- Compensation
- $170,000 to $210,000 plus 0.4% to 0.9% equity
Wander turns a destination, dates, a budget and a handful of tastes into a paced, walkable itinerary. The planning system is the product: how the model is prompted and grounded, how days are kept walkable, how pacing is enforced, and the evaluation set every change is measured against.
You would be an early engineer, and the work decides whether people trust the plan. A day that looks good but sends someone across the city and back is worse than a plainer day that flows.
What you would own
- Own the design and adapt loops: prompting, grounding, validation and the fallback planner.
- Build the evaluation set. Every change is judged against real trips with known-good shapes before it ships.
- Keep days walkable and paced. Catch the plan that reads well and walks badly.
- Make the model-agnostic layer real: routing, fallback and cost, across more than one provider.
What we are looking for
- Five or more years building systems other people depend on, with real applied-ML or LLM product work.
- You have opinions about evaluation that came from being burned.
- You write TypeScript comfortably, or you will within a fortnight.
- You care about the difference between a demo and a plan someone follows on the ground.
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 two conversations with people you would work alongside. Four steps, usually inside two weeks. We tell you where you stand at every one, and we reply either way.