ML Platform Engineer: Inference & Production

Xapply; San Francisco (CA); On-site; USD 190,000 - 230,000; Full time

Job summary

OpenAI seeks a software engineer to build and evolve its classification and evaluation platform. You will design services, APIs, and pipelines that enable researchers and data scientists to run experiments at scale with reliability.

You’ll own production aspects from architecture to deployment, optimize inference performance, and improve observability to support fast iteration in a demanding ML environment.

Qualifications

• Experience designing and building scalable API services.
• Strong background in distributed systems and production engineering.
• Ability to diagnose complex production issues and tradeoffs.
• Experience collaborating with researchers and data scientists.

Responsibilities

• Design and implement services and APIs for classification and evaluation.
• Build online and offline pipelines for fast experimentation.
• Improve model-serving performance and resource efficiency.
• Ensure reliability, observability, and incident response.
• Collaborate with ML engineers and researchers to ship features.
• Shape architecture with ownership from design to production.

Skills

API design

Concurrency

Caching

Performance optimization

Failure recovery

Observability

Job description

OpenAI seeks a software engineer to build and evolve its classification and evaluation platform. You will design services, APIs, and pipelines that enable researchers and data scientists to run experiments at scale with reliability.

You’ll own production aspects from architecture to deployment, optimize inference performance, and improve observability to support fast iteration in a demanding ML environment.