AI Framework Software Engineer - vLLM

Location: On-site in Shanghai, China

Company

AI engineering work focused on developing software frameworks and performance solutions for artificial intelligence products.

What you will do

• Design, develop, and optimize AI frameworks including vLLM and PyTorch.
• Implement distributed algorithms for model and data parallelism, including asynchronous data communication.
• Transform neural-network computational graphs and develop machine-learning primitives for mathematical libraries.
• Profile distributed deep-learning models, identify bottlenecks, and implement performance improvements across hardware backends.
• Collaborate with deep-learning researchers to integrate advances into AI frameworks.
• Contribute to open-source projects while following industry standards.

Requirements

• Master’s degree in Computer Science, or a bachelor’s degree with at least two years of relevant experience.
• Proficiency in Python and C++.
• Foundational knowledge of vLLM, PyTorch, and deep-learning concepts.
• Ability to debug and optimize software performance.
• Effective written and spoken English is required.
• On-site presence in Shanghai, China is required.

Nice to have

• Experience with performance-optimization technologies and techniques.
• Experience with large language models and inference stacks.
• Open-source contribution or collaboration experience.
• Familiarity with GPU architecture and concepts.
• Strong problem-solving and technical analysis skills.

Culture & Benefits

• Full-time college graduate position.
• Work is performed on-site under Shift 1 in China.
• Collaboration with AI researchers and engineers on open-source and industry-standard solutions.
• No recruitment, medical examination, or other hiring fees are charged.