AI Infrastructure Engineer

About this role

Meshy is seeking an AI Infrastructure Engineer to enhance its AI model serving stack by optimizing reliability and scalability. The role involves building and scaling inference infrastructure and requires a strong background in backend or infrastructure engineering, particularly in cloud-native environments.

What you'll do

• Build and scale AI inference infrastructure from the ground up.
• Design CPU/GPU resource management systems for optimization.
• Implement GPU scheduling and multiplexing technologies.
• Optimize the inference pipeline for performance and stability.
• Contribute to system reliability and disaster recovery.
• Explore AI-native infrastructure and automated operations.

What they're looking for

• 3–5 years of backend or infrastructure engineering experience.
• Proficiency in Go or Python.
• Understanding of Linux internals and distributed systems.
• Experience with Kubernetes, Docker, and microservices.
• Knowledge of inference systems and resource management.
• Self-driven with strong ownership skills.

Benefits

• Competitive salary and equity.
• Comprehensive benefits package.
• [Unknown]
• [Unknown]
• [Unknown]
• [Unknown]