AI Contract Spend Leakage Detector

Orvix Works

Remote · $130k – $160k / year · Full-time · Posted 4 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

Spend leakage is the gap between what a company negotiated in a vendor contract and what it actually pays. A contract that specifies $85/hour rates for consulting services gets honored — except for the 340 invoices where the rate was $87/hour because a line item was miscoded. Multiplied across hundreds of vendors and thousands of invoices, most large enterprises leak 2-8% of their addressable spend. We serve procurement teams at 60 enterprise clients processing $14B in combined vendor spend annually. Spend leakage detection requires cross-referencing invoice data against contract terms at line-item level — a problem that's hard to do manually at scale and easy to solve with ML once the right signals are engineered. You'll own the leakage detection system: building the contract term extraction pipeline (what does this master services agreement actually commit to?), designing the invoice-to-contract matching logic, and implementing the anomaly detection that flags where invoiced amounts diverge from contractual rates, volume thresholds, or discount structures. The ROI is concrete and measurable — every percentage point of leakage recovered on $14B is $140M.

Fully remote.

Responsibilities

Build contract term extraction pipeline parsing rate cards, volume commitments, and discount structures from MSAs
Design invoice-to-contract matching logic for line-item rate and volume verification
Implement anomaly detection identifying invoiced amounts diverging from contractual terms
Create leakage categorization classifying root causes: pricing errors, term misapplication, unauthorized charges
Build procurement dashboard surfacing leakage findings for client action
Validate detection accuracy against manually audited invoice samples

Requirements

6+ years in data science, procurement analytics, or spend analytics
Experience with contract or invoice data processing at enterprise scale
Strong Python, SQL, and NLP skills for document understanding
Familiarity with procurement processes, vendor contracts, and enterprise spend management
Track record delivering measurable financial outcomes from analytics work