Profile cover
C

AI Transaction Categorization Engineer

Cole Mueller

Full-time · Job · New_York

About the role

Categorizing a bank transaction sounds simple until you realize that "AMZN*2847XJ" could be groceries, electronics, or a subscription renewal — and your user's budget depends on getting it right. We process 80 million transactions per month for personal finance apps, and our categorization model needs to be right 96% of the time because every miscategorization erodes user trust. The current system is a hybrid: a rule engine handles the obvious merchants, and an ML model handles everything else. The rule engine covers 55% of volume at 99.5% accuracy. The ML model covers the remaining 45% at 91% accuracy. Your job is to close that gap — improving the ML model to 96%+ while maintaining sub-50ms latency at our throughput. You'll have access to labeled transaction data across 8 financial institutions, each with slightly different formatting conventions. The labeling pipeline produces 50,000 new training examples per week from user corrections. You'll own the full model lifecycle from feature engineering through deployment and monitoring.

Responsibilities

  • Improve transaction categorization accuracy from 91% to 96%+ on ML-classified transactions
  • Engineer features from raw transaction strings, amounts, and temporal patterns
  • Maintain the model training, evaluation, and deployment pipeline
  • Build active learning loops using user correction data
  • Monitor model performance across different financial institutions
  • Optimize inference latency to stay under 50ms at 80M monthly transactions

Requirements

  • 5+ years in NLP or text classification with production deployment experience
  • Experience with model serving at high throughput and low latency
  • Strong Python and PyTorch skills
  • Proficiency in SQL for feature engineering and analysis
  • Understanding of precision-recall trade-offs in multi-class classification

Benefits

  • Fully remote with flexible hours
  • Comprehensive health coverage
  • 401(k) with match
  • $3,500 annual professional development budget
  • Quarterly team meetups

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$100k – $130k / year

AI Expertise

AI & Machine Learning Engineers NLP & Prompt Engineering

Skills

python pytorch sql fastapi docker pandas

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile

Interested in this role? Create your free profile to apply.

Apply — create free profile