Infrastructure Engineer (AI/ML)

Location: Beijing (Hybrid)

Company

hirify.global is a leading 3D generative AI company transforming content creation by enabling users to generate 3D assets from text and images in minutes.

What you will do

• Build and scale AI inference infrastructure, including serving, scheduling, and orchestration.
• Design and optimize CPU/GPU resource management systems for maximum cost-efficiency.
• Implement production-level GPU scheduling and multiplexing technologies like MIG and MPS.
• Optimize inference pipelines for throughput, latency, and stability under high concurrency.
• Contribute to system reliability, disaster recovery, and cloud cost governance.

Requirements

• 3–5 years of experience in Backend or Infrastructure engineering.
• Strong mastery of Go or Python with solid engineering foundations.
• Deep understanding of Linux internals, networking, and distributed systems.
• Proven hands-on experience with Kubernetes, Docker, and microservices.
• Prior project experience in inference systems, task scheduling, or resource management.
• Must be based in or able to work from the Beijing office.

Nice to have

• Experience with GPU platforms or customizing Kubernetes schedulers.
• Familiarity with Ray, model serving frameworks, or distributed inference architectures.
• Practical experience with GPU multiplexing technologies (MIG, MPS, vGPU).
• Engineering background in SRE, observability, or cloud cost optimization.

Culture & Benefits

• Competitive salary, equity, and stock options for core team members.
• Comprehensive health, dental, and vision insurance.
• 401(k) plan.
• Flexible work environment with hybrid options.
• Unlimited, flexible time off.