Machine Learning Infrastructure Engineer

Astera Labs is seeking a Machine Learning Infrastructure Engineer to build and maintain the operational backbone for modern AI systems. This role focuses on developing the runtime, platform, and infrastructure for LLM applications, agents, and model-backed workflows, ensuring reliability, observability, and cost-efficiency at scale.

• Build and improve internal AI infrastructure for LLM applications and agents
• Own inference deployment paths across managed and self-serve environments
• Develop AI Ops capabilities including evaluation, observability, and cost monitoring
• Improve performance and unit economics through optimization techniques
• Create reusable APIs and platform abstractions for AI systems
• 1-5 years of experience in software engineering, ML infrastructure, or MLOps