Founding Engineer - LLM Infra & Platform
$140k - $220k • San Francisco • FullTime
Posted 1mo ago
Remote Work Policy
On-site
Employment Type
FullTime
Categories
LLM Engineer
About the job
Pax Historia is building the platform for worldbuilders, storytellers, and game developers to create and publish interactive entertainment. With over 25,000 user-published presets and more than 92 million rounds played, the company has secured a $10M+ seed round. This role focuses on owning the system responsible for sending a high volume of requests across multiple AI providers, ensuring quick, reliable, and cost-effective responses. The engineer will work on provider reliability, structured outputs, caching, routing, and monitoring to manage over 37 models and approximately 240 billion weekly tokens, while reducing costs and latency for a large daily active user base. This position does not involve model training or running model inference.
Responsibilities
- Own the system for sending requests across AI providers, ensuring speed, reliability, and cost-effectiveness.
- Improve provider reliability, implement structured outputs, caching, routing, and monitoring.
- Ensure 37+ models reliably handle ~240 billion weekly tokens.
- Reduce costs and latency for 60k+ daily active users.
Requirements
- Strong fundamentals and ability to learn quickly.
- Obsessed with detail, data-oriented, and a tendency to verify everything.
Benefits
- Meaningful equity as a founding engineer.
- Visa sponsorship available.