AI Infrastructure Engineer

AI Infrastructure Engineer ABOUT MESHY Headquartered in Silicon Valley, Meshy is the leading 3D generative AI company on a mission to Unleash 3D Creativity by transforming the content creation pipeline. Meshy makes it effortless for both professional artists and hobbyists to create unique 3D assets—turning text and images into stunning 3D models in just minutes. What once took weeks and cost $1,000 now takes just 2 minutes and $1. Our world-class team of top experts in computer graphics, AI, and art includes alumni from MIT, Stanford, and Berkeley, as well as veterans from Nvidia and Microsoft. Our talent spans the globe, with team members distributed across North America, Asia, and Oceania, fostering a diverse and innovative multi-regional culture focused on solving global 3D challenges. Meshy is trusted by top developers, backed by premiere venture capital firms like Sequoia and GGV, and has successfully raised $52 Million in funding. Meshy is the market leader, recognized as the No.1 in popularity among 3D AI tools (according to 2024 A16Z Games) and No.1 in website traffic (according to SimilarWeb, with 3 Million monthly visits). The platform boasts over 5 Million users and has generated 40 Million models. Founder and CEO Yuanming (Ethan) Hu earned his Ph.D. in graphics and AI from MIT, where he developed the acclaimed Taichi GPU programming language (27K stars on GitHub, used by 300+ institutes). His work is highly influential, including an honorable mention for the SIGGRAPH 2022 Outstanding Doctoral Dissertation Award and over 2,700 research citations. ABOUT THE ROLE - This role sits at the intersection of platform engineering, site reliability, and applied ML systems. The function owns the reliability, scalability, and operability of Meshy's AI model serving stack, along with core engineering infrastructure. The team operates a conventional production infrastructure (CI/CD, build systems, deployment, runtime environments) and develops a model-serving platform that connects the models developed by our Research Team to product-facing backend systems. The position is systems-heavy, production-oriented, and focused on turning experimental model artifacts into robust, observable, and cost-efficient services. JOB RESPONSIBILITIES - 0-1 to 1-N Infrastructure: Build and scale AI inference infrastructure from the ground up, including inference serving, scheduling, orchestration, and auto-scaling. - Resource Management: Design and optimize CPU/GPU resource management systems to maximize utilization and cost-efficiency. - GPU Virtualization: Drive the production-level implementation of GPU scheduling and multiplexing technologies (MIG, MPS, Virtualization). - Performance Optimization: Optimize the inference pipeline (throughput, latency, and stability) to support high-concurrency and complex business scenarios. - System Reliability & Governance: Contribute to system stability, disaster recovery design, and cloud cost management/governance. - AI-Native Evolution: Explore AI-native infrastructure and automated O&M (Operations & Maintenance) to support rapid business growth. QUALIFICATIONS - Experience: 3–5 years of experience in Backend or Infrastructure engineering (Cloud-native or AI platform experience is highly preferred). - Technical Proficiency: Strong mastery of Go or Python with solid engineering foundations and clean coding habits. - Core Fundamentals: Deep understanding of Linux internals, networking, and distributed systems. - Cloud Native: Proven hands-on experience with Kubernetes, Docker, and microservices architecture. - Domain Expertise: Prior project experience in inference systems, task scheduling, or resource management. - Soft Skills: Highly self-driven, quick learner, and eager to take on significant ownership in a fast-paced startup environment. NICE TO HAVE - Experience with GPU platforms or customizing Kubernetes schedulers. - Familiarity with Ray, model serving frameworks, or distribut ... (truncated, view full listing at source)