AI Procurement Spend Analytics Developer

Orvix Works

Remote · $100k – $130k / year · Full-time · Posted 5 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

Enterprise procurement teams manage thousands of suppliers and millions of purchase orders, but most can't answer basic questions: "How much did we spend on IT consulting last quarter?" The data exists across 15 ERP systems, each using different category codes, supplier naming conventions, and currency formats. Our spend analytics platform normalizes this mess into a single source of truth. The NLP challenge is spend classification — taking a purchase order line item like "Professional services — Phase 2 implementation support per SOW #4523" and mapping it to the right category in a 4-level taxonomy. Rule-based approaches get 60% accuracy; our ML models achieve 89%. You'll push that to 95% by handling the long tail of ambiguous line items that don't fit neatly into any category. The procurement analytics team is four engineers. You'll own the classification pipeline and work with domain experts who define the taxonomy and review edge cases.

Fully remote.

Responsibilities

Improve spend classification accuracy from 89% to 95% on ambiguous line items
Build features from purchase order text, supplier metadata, and historical patterns
Design active learning workflows for edge case resolution
Handle multi-currency normalization and cross-ERP data harmonization
Create dashboards surfacing spend insights for procurement teams
Maintain classification taxonomy as new categories emerge

Requirements

5+ years in NLP or text classification with production systems
Experience with enterprise data: ERP systems, purchase orders, or financial data
Strong Python and SQL skills for data processing at scale
Understanding of classification under noisy, ambiguous labels
Ability to work with domain experts on taxonomy refinement