Production AI Infra Engineer — Scale, Reliability, Costs

present of AI; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

PlayerZero builds a living model of production software to predict and prevent customer-facing issues before code ships. The AI infrastructure engineer role focuses on keeping model serving systems fast, reliable, and cost-efficient while supporting evolving ML workloads.

You will work close to AI development, deploying models behind APIs, tracking performance, and improving pipelines for scalable inference and monitoring in production.

Qualifications

• Solid software engineering fundamentals and production-grade coding practices.
• Hands-on cloud experience and familiarity with containerized deployments.
• Working grasp of model serving and data pipelines to support ML workloads.

Responsibilities

• Build and run systems that train, serve and monitor models.
• Focus on reliability, cost and speed of inference and training pipelines.
• Collaborate with teams to maintain scalable, observable infrastructure.

Skills

Software engineering

Cloud experience

Container technologies

Model serving

Data pipelines

Tools

Cloud platforms

Container technologies

Job description

PlayerZero builds a living model of production software to predict and prevent customer-facing issues before code ships. The AI infrastructure engineer role focuses on keeping model serving systems fast, reliable, and cost-efficient while supporting evolving ML workloads.

You will work close to AI development, deploying models behind APIs, tracking performance, and improving pipelines for scalable inference and monitoring in production.