Every LumaLedger account is a complete, reconciled history of a household's money. The opportunity is to say something useful about it: which subscription quietly doubled, what next month looks like, whether this is a bad month or a bad year, where the same dollar is being counted twice.
You would define what we measure, build the models that produce those insights, and be accountable for them being right — because an insight that is wrong in personal finance is worse than no insight at all.
What you would do
- Build forecasting, anomaly detection and recurring-charge models on ledger data.
- Define the product analytics that tell us whether a feature helped.
- Design experiments honestly, including the ones that fail.
- Publish internal analysis people actually read.
What we look for
- 4+ years in data science or applied ML with production impact.
- Excellent SQL and Python; you are comfortable in a real warehouse.
- You can explain a method to a marketer and defend it to an engineer.
Nice to have, never required
- Time series and seasonality at consumer scale.
- Experience with consumer finance or transaction data.
If you are on the fence
Every list above describes the person we imagine, not a checklist we score. People who meet most of it and want the rest have done extremely well here. If the role reads like the job you want next, that is enough reason to write to us — tell us which part you would have to grow into and we will be straight with you about whether it works.
Send whatever shows your work best — a CV, a repository, a portfolio, or a few paragraphs. A hiring manager reads every one, and you will hear back within two business days.
Apply by emailcareers@lumaledger.app