Skip to main content

Pax Historia

Founding Engineer - LLM Infra & Platform

  • Confirmed live in the last 24 hours
  • $140k–$220k
  • Mid level
  • Full-time
  • On-site · San Francisco
  • Added 1 month ago

About this role

Pax Historia is seeking a Founding Engineer to build and maintain the infrastructure powering their interactive entertainment platform. This role focuses on ensuring the reliability, efficiency, and cost-effectiveness of their LLM-based system, handling a high volume of requests and tokens. You'll be crucial in supporting a rapidly growing user base and shaping the future of worldbuilding and storytelling.

What you'll do

  • Maintain provider reliability for AI models.
  • Optimize structured outputs from AI models.
  • Implement caching strategies.
  • Develop routing mechanisms for AI requests.
  • Establish and monitor system performance.
  • Reduce costs and latency for users.

What they're looking for

  • Caching
  • Routing
  • Monitoring
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Pax Historia

View all jobs at Pax Historia

Likely interview questions

  • Describe your experience with designing and scaling distributed systems.
  • How would you approach troubleshooting a sudden spike in latency for AI requests?