AI Expense Report Anomaly Detection Engineer

Holtix Solutions

Remote · $60k – $80k / year · Full-time · Posted 3 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Finance still catches duplicate expense claims manually, three weeks after reimbursement already went out. By then the money's gone and getting it back is its own process. We want to catch it before approval, not after. You'll build an anomaly detection layer on top of our existing invoice and receipt extraction pipeline, flagging duplicate submissions, out-of-policy amounts, and unusual vendor patterns before an expense report gets approved. Small team, fast shipping. You'll have your first detection rules in production within the first month, then iterate based on what finance teams actually flag as false positives.

Fully remote.

Responsibilities

Build anomaly detection rules for duplicate and out-of-policy expense claims
Integrate detection into the existing receipt extraction pipeline
Reduce false positives based on direct finance team feedback
Ship initial detection rules within the first month
Monitor detection accuracy as new expense categories are added

Requirements

Comfortable with Python and pandas for anomaly detection logic
Basic scikit-learn experience for classification models
SQL fluency for querying expense and vendor data
Entry-level friendly, mentorship provided by senior document processing engineers