Latest AI JobsBrowse Jobs
Meshy logo

AI Infrastructure Engineer

MeshyBeijingEngineering
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Posted
20 Mar 2026
Status
Open · checked 7d ago

About this role

Role Overview

The AI Infrastructure Engineer position at Meshy is a remote-friendly opportunity based in Beijing that focuses on platform engineering, site reliability, and applied machine learning systems. This role suits an experienced engineer who wants to own the reliability, scalability, and operability of an advanced AI model serving stack and core engineering infrastructure. Working at the intersection of research and production, the professional in this role will turn experimental machine learning model artifacts into robust, observable, and cost-efficient services for product-facing backend systems.

Key Responsibilities

Build and scale AI inference infrastructure from the ground up, covering inference serving, scheduling, orchestration, and auto-scaling.
Design and optimize CPU and GPU resource management systems to maximize hardware utilization and cost-efficiency.
Implement production-level GPU scheduling and multiplexing technologies, including MIG, MPS, and virtualization.
Optimize the inference pipeline for throughput, latency, and stability to support high-concurrency demands and complex business scenarios.
Contribute to overall system stability, disaster recovery design, and cloud cost management and governance.
Explore AI-native infrastructure and automated operations and maintenance to support rapid company growth.

Requirements

Bring 3 to 5 years of professional experience in backend or infrastructure engineering, with a preference for cloud-native or AI platform backgrounds.
Demonstrate strong technical proficiency in Go or Python, backed by solid engineering foundations and clean coding habits.
Possess a deep understanding of Linux internals, computer networking, and distributed systems.
Show proven, hands-on experience working with Kubernetes, Docker, and microservices architecture.
Offer prior project experience dealing with inference systems, task scheduling, or resource management.
Exhibit a highly self-driven work ethic as a quick learner who is eager to assume significant ownership in a fast-paced startup environment.

Nice to Have

Hands-on experience working with GPU platforms or customizing Kubernetes schedulers.
Familiarity with Ray, model serving frameworks, or distributed inference architectures.
Practical experience applying GPU multiplexing technologies such as MIG, MPS, or vGPU.
Previous engineering background in site reliability engineering, observability, or cloud cost optimization.
Active contributor status to open-source projects or recognized technical influence within the tech community.

Skills and Tools

Python
Go
Kubernetes
Docker
Linux
Microservices Architecture
GPU Virtualization (MIG, MPS, vGPU)
Distributed Systems

Salary and Benefits

Competitive salary paired with equity and a comprehensive benefits package.
Stock options available for core team members.
401(k) retirement plan.
Comprehensive health, dental, and vision insurance coverage.
Flexible work environment with options for remote arrangements.
Unlimited, flexible time off.
Provision of the latest and best office equipment.

About the Company

Headquartered in Silicon Valley with a distributed global team across North America, Asia, and Oceania, Meshy is a leading 3D generative AI company. The organization focuses on transforming the content creation pipeline to make 3D asset generation effortless for professionals and hobbyists alike. Backed by premiere venture capital firms like Sequoia and GGV with $52 million in funding, the platform serves millions of users worldwide and leads the market in traffic and popularity among 3D AI tools.

How to Apply

Candidates interested in this position should visit the official company careers page to submit an application.

Skills and tech stack

PythonKubernetesDocker

Questions candidates ask

What is the primary focus of the AI Infrastructure Engineer role?

The role focuses on building, scaling, and optimizing Meshy's AI model serving stack, bridging research models with product-facing backend systems through robust infrastructure.

Is remote work available for this position?

Yes, Meshy offers a flexible work environment with options for remote work alongside its Beijing location.

What technical background is required for applicants?

Applicants need 3 to 5 years of backend or infrastructure engineering experience, proficiency in Python or Go, and hands-on experience with Kubernetes, Docker, Linux internals, and distributed systems.

What tools and technologies are frequently used in this job?

Key technologies include Python, Go, Kubernetes, Docker, Linux, microservices architecture, and GPU virtualization technologies like MIG and MPS.

What benefits are provided by Meshy?

Meshy offers a competitive salary, stock options, a 401(k) plan, health, dental, and vision insurance, unlimited flexible time off, and the latest office equipment.

Ready to apply?

The application is on the official Meshy careers page.

Apply on company site