Back to jobs

Founding Engineer - LLM Infra & Platform

Pax Historia
San FranciscoFull-time$140,000 – $220,000 / year

Upload your resume once and Scout applies for you

Apply with Scout
Share this job:LinkedInXSave image

You’ll own the infrastructure that routes requests from Pax Historia’s interactive games to external AI providers, with a focus on reliability, speed, and cost. The work includes improving provider routing, structured outputs, caching, and monitoring; the role does not involve training models or running inference in-house.

  • Permanent
  • On-site

Skills and expertise

AI provider integrationRequest routingCachingStructured outputsMonitoringReliability engineeringLatency optimizationCost optimization

Key responsibilities

  • Improve reliability across the AI providers used by Pax Historia’s games.
  • Reduce request costs and latency for the platform’s daily users.
  • Build and monitor systems for routing, caching, and structured outputs.

How this job compares

Compared with 362 open mid-level infrastructure jobs on November 21, 2026.

Pay
This job pays $140K to $220K a year. The 96 open mid-level infrastructure jobs that publish US pay start at $170K on average, so this job starts about 18% lower.
Similar open jobs
We Love AI Jobs lists 362 open mid-level infrastructure jobs at 144 companies.
Remote work
This job is on site. 57 of the 362 mid-level infrastructure jobs (16%) are remote.
AI in this role
High. AI is the core of the work: building, training or deploying AI systems. The role directly owns the system that sends large volumes of requests to AI models and manages their responses. Although it does not involve model training or in-house inference, AI infrastructure is the central focus of the job.

Full description

Company

Pax Historia is creating the future of interactive entertainment.

We’re building the platform for worldbuilders, storytellers, and game devs to create and publish any ‘what if’ they can think of. So far, most of the 25k+ user published presets on our site are historical (eg, ‘what if Rome never fell?’), but fantasy and sci fi are the fastest growing categories on the site.

We have seen over 92 million rounds played and raised a 10M+ seed round in March. We’re backed by Y Combinator (W26), Bessemer, Pace Capital, Z Fellows, and more.

Role

Every game on Pax Historia depends on our ability to send huge numbers of requests across many AI providers and get the right response back quickly, reliably, and cheaply.

We’re hiring an engineer to own that system. You’ll work on provider reliability, structured outputs, caching, routing, and monitoring. At the end of the day, you will need to:

• Ensure that the 37+ models on our site reliably handle our ~240 billion weekly tokens.

• Reduce costs and latency for our 60k+ daily active users wherever possible.

You will not be in charge of model-training. We do not run model inference ourselves.

If you’re obsessed with detail, data oriented, and have a strong tendency to verify everything, then this might be a great fit for you. We don’t expect you to have done this exact job before, but we are expecting you to be a fast learner with extremely strong fundamentals.

Logistics

You’ll be our 7th team member. We work in-person in San Francisco, 5+ days/week. We are open to sponsoring visas.

Comp will include meaningful equity to reflect your responsibility as a founding engineer.

Upload your resume once and Scout applies for you

Apply with Scout

Similar jobs