Founding LLM Infra Engineer — Scale Platform Reliability

Pax Historia; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity

Visa sponsorship

Job summary

Pax Historia in San Francisco is seeking an engineer to own the system that routes requests across 37+ models and 60k+ daily users. You’ll focus on provider reliability, structured outputs, caching, routing, and monitoring to keep latency low and costs down.

We value fast learners with strong fundamentals; you won't train models, but you will verify everything, measure impact, and own reliability end-to-end in a founding-engineer capacity, with meaningful equity and visa sponsorship.

Qualifications

• Must have strong fundamentals, data-oriented mindset and a penchant for verification.
• Experience improving reliability and performance of distributed systems.
• Ability to reduce costs and latency while handling large-scale traffic.

Responsibilities

• Own and operate the system that routes requests across many AI providers.
• Ensure reliability of 37+ models handling 30B+ monthly tokens.
• Implement caching, routing, and monitoring to reduce latency and cost.

Skills

Reliability engineering

System monitoring

Performance tuning

Data analysis

Cost optimization

Tools

Monitoring tools

Caching layers

Routing

Job description

Pax Historia in San Francisco is seeking an engineer to own the system that routes requests across 37+ models and 60k+ daily users. You’ll focus on provider reliability, structured outputs, caching, routing, and monitoring to keep latency low and costs down.

We value fast learners with strong fundamentals; you won't train models, but you will verify everything, measure impact, and own reliability end-to-end in a founding-engineer capacity, with meaningful equity and visa sponsorship.