mid software engineering Solutions Architect ic · Posted Apr 20, 2026

About this role

Nvidia is hiring a mid-level Solutions Architect in the software engineering function based in Beijing, China. The posting calls out experience with Machine Learning, LLMs, Data Structures, Performance Optimization.

Role
Solutions Architect
Function
software engineering
Level
mid
Track
Individual contributor
Employment
Full-time
Location
Beijing, China
Posted
Apr 20, 2026

More roles at Nvidia

Senior CI/CD Engineer
Santa Clara, CA · senior
AWS GCP Azure
Senior Board Test Engineer
Santa Clara, CA · senior
Python Bash Testing
Manager, System Test Engineering
Taipei, Taiwan · manager
Python Bash Testing
Senior Board Test Engineer
Santa Clara, CA · senior
Python Bash Testing
System Level Test Engineer
Santa Clara, CA · mid
Python Linux Testing
All Nvidia jobs →

Job description

from Nvidia careers

NVIDIA is leading company of AI computing. At NVIDIA, our employees are passionate about AI, HPC, GAMING. Our SA team is more focusing to bring NVIDIA new technology into difference industries. We help to design the architecture of AI computing platform, analysis the AI and HPC applications to deliver our value to customers, focusing on defining and solving computational challenges in LLM inference and training acceleration, as well as network communication and data transfer optimization.

What You'll Be Doing:

  • Contribute to the development of open-source inference frameworks such as SGLang and vLLM, including feature and operator development, performance optimization, and model support, in collaboration with the community.

  • Develop and optimize KV cache offloading frameworks for LLM workloads, supporting multi-level cache offloading and reuse across CPU, SSD, and remote storage to improve inference efficiency. (Team project: FlexKV)

  • Drive R&D on compute performance in distributed training, and explore methods and technologies for performance optimization.

  • Study computational challenges in machine learning systems, identify common needs and bottlenecks, and build example code, acceleration libraries, or frameworks accordingly.

What We Need to See:

  • Over 10 years working experience in the technology industry, with master’s degree or above in computer science, mathematics, electrical engineering, automation, or related fields.

    This is an excerpt. Read the full job description on Nvidia careers →
All software engineering jobs software engineering in Beijing, China Jobs in Beijing, China software engineering salaries software engineering career path
All Nvidia Jobs Browse software engineering roles mid positions