Profile cover
O

AI Token Budget Management System Developer

Owen Goldberg

Full-time · Job · Chicago

About the role

LLM API costs are unpredictable. A single runaway prompt chain can consume $500 in tokens before anyone notices. Our token budget management system gives engineering teams real-time visibility and control: per-project token budgets, real-time usage tracking, cost alerts, and automatic throttling when budgets are exceeded. As a junior developer, you'll build the usage tracking and alerting pipeline: intercepting token consumption events from our LLM proxy, aggregating usage by team, project, and model, computing real-time budget utilization, and triggering alerts when consumption exceeds configurable thresholds. It's mostly Python, SQL, and API work — straightforward engineering on a problem that every AI team faces. The platform economics team is three engineers. You'll start with the usage aggregation module, learning how token consumption patterns vary across different use cases. Your senior teammate handles the throttling and rate limiting logic; you provide the consumption data that drives their decisions.

Responsibilities

  • Build usage tracking intercepting token consumption from the LLM proxy
  • Aggregate token usage by team, project, model, and time period
  • Compute real-time budget utilization and remaining allocations
  • Implement alerting when consumption exceeds configurable thresholds
  • Create usage dashboards for engineering team budget visibility
  • Document usage patterns and cost optimization opportunities

Requirements

  • 1+ year of Python development with API and database experience
  • Familiarity with SQL for aggregation and reporting queries
  • Basic understanding of REST APIs and event processing
  • Interest in cloud cost management and FinOps
  • Attention to accuracy for financial usage tracking

Benefits

  • Fully remote with flexible schedule
  • Health and dental insurance
  • $1,500 learning stipend
  • Mentorship from senior platform engineers
  • Solve a problem every AI team struggles with

Keep exploring related roles

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

Job Type

Full-time

Level

Junior

Language

English

Salary Range

$60k – $80k / year

AI Expertise

MLOps & AI Infrastructure AI Product & Strategy

Skills

python sql fastapi docker aws 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