全职 Senior Distributed Systems - AI Infrastructure Engineer 工作, 薪水, NEXadept 公司招聘中 - Ricebowl

About the Role

We are looking for a Senior Distributed Systems & AI Infrastructure Engineer to build and optimize the infrastructure powering next-generation AI inference at global scale.

You will work on high-performance distributed systems supporting large-scale model serving across thousands of GPUs and other accelerators. The role sits at the intersection of distributed systems, performance engineering, networking, and AI infrastructure, with a strong focus on building systems that are fast, scalable, and highly reliable.

Key Responsibilities

• Design and develop high-performance distributed systems for large-scale AI inference.
• Build scalable infrastructure for model serving across large GPU and accelerator clusters.
• Optimize system latency, throughput, resource utilization, and reliability.
• Design and improve high-performance networking and I/O components.
• Investigate and resolve complex issues across distributed systems and large-scale infrastructure.
• Develop performance-critical components using Rust, Go, or C++.
• Improve the scalability and reliability of infrastructure supporting next-generation AI workloads.
• Work closely with infrastructure, ML, and systems teams to identify and solve performance bottlenecks.

Requirements

• Bachelor's degree or equivalent experience in Computer Science, Engineering, or a related technical field.
• Strong systems programming experience in Rust, Go, or C++.
• Proven experience designing and building high-performance distributed systems at scale.
• Strong understanding of networking, network protocols, and high-performance I/O.
• Strong debugging and problem-solving skills for complex distributed systems.
• Experience optimizing systems for performance, scalability, and reliability.

Preferred Qualifications

• Experience with AI/ML serving infrastructure or large-scale inference systems.
• Familiarity with disaggregated inference architectures.
• Understanding of GPU programming models and GPU memory hierarchies.
• Experience with GPU networking and interconnect technologies such as NVLink, InfiniBand, or RoCE.
• Experience working with large-scale GPU clusters or accelerator infrastructure.
• Knowledge of performance optimization, profiling, and systems benchmarking.
• Experience supporting large-scale AI model training or inference workloads.