About the Team

• Relies on a large and growing GPU fleet for inference workloads
• Develops systems and tools for introducing new models, managing deployments, and ensuring effectiveness at scale
• Spans distributed systems, platform engineering, infrastructure automation, and developer experience

About the Role

• Looking for a software engineer experienced in building or operating large-scale production systems
• Design and develop systems supporting model lifecycle in production
• Help transform operational processes into scalable platform capabilities

In This Role, You Will

• Build and evolve the platform for deploying, configuring, and managing models
• Develop systems for deployment orchestration, model rollouts, and more
• Create abstractions and tooling to simplify infrastructure and improve developer experience
• Automate operational workflows and improve reliability and scalability
• Partner with various teams to deliver reusable platform capabilities
• Shape the technical direction of the model management platform

You Might Thrive in This Role If You

• Have experience with internal platforms, distributed systems, or large-scale infrastructure
• Enjoy solving complex operational problems and building reliable software abstractions
• Understand deployment systems, observability, and incident response
• Care about developer experience and collaboration

Qualifications

• Five or more years of software engineering experience in production infrastructure
• Strong programming skills in Go, Python, C++, Rust, or equivalent
• Experience in designing highly available distributed systems
• Experience in platform, infrastructure, or production engineering
• Strong systems design, debugging, and communication skills