AI Infrastructure Engineer

About the Company

Meshy is the leading 3D generative AI company on a mission to transform the content creation pipeline. By turning text and images into stunning 3D models in minutes, Meshy empowers both professional artists and hobbyists. Backed by Sequoia and GGV, the company serves over 5 million users and is a market leader in 3D AI tools.

Responsibilities

• Design, develop, and optimize core capabilities for the AI inference platform, including task scheduling and service orchestration
• Develop CPU/GPU resource management systems to optimize stability and cost efficiency
• Drive unified management of GPU resources using technologies like MIG, MPS, and virtualization
• Optimize throughput, latency, and availability of the inference pipeline in high-concurrency scenarios
• Focus on R&D efficiency, disaster recovery architecture, and automated operations

Requirements

• Bachelor’s degree or higher in Computer Science, Software Engineering, AI, or related fields
• 1 to 3 years of experience in backend development, infrastructure, or AI platforms
• Proficiency in Go or Python
• Strong understanding of Linux, operating systems, computer networks, and distributed systems
• Practical experience with Kubernetes, Docker, or microservices
• Real-world project experience in model inference or resource scheduling

Preferred Qualifications

• Experience with GPU inference platforms or Kubernetes schedulers
• Familiarity with Ray or Ray Serve
• Knowledge of MIG, MPS, vGPU, or GPU resource reuse
• Engineering experience in observability, SRE, or capacity planning
• Contributions to open-source projects or technical blogs

Benefits

• Competitive salary and equity
• Flexible work environment (remote and on-site options)
• Unlimited, flexible time off
• 401(k) plan
• Comprehensive health, dental, and vision insurance
• Stock options for core team members