l
lxfang

LiXiaofang

@lxfang

token

Chine
Anglais
Certaines informations sont présentées en anglais.
À propos de moi
I’m a dedicated AI computing & token technical specialist with over 2 years of industrial experience focusing on GPU cluster deployment, large model reasoning optimization, token quota calculation, API docking and cost optimization for LLM services. My core service covers mainstream LLMs (GPT series, Llama, Mistral, Qwen), multimodal generation model computing & token management, from on-premise GPU cluster to cloud elastic token resource supply.... Plus d’infos

Compétences

l
lxfang
LiXiaofang
hors ligne • 
Temps de réponse moyen de 1 heure

Voir mes services

Consulting
I will ai computing and token

Expérience professionnelle

NVIDIA

AI Computing & Token Operation Specialist

NVIDIA • Temps plein

Jun 2024 - Present2 yrs

Managed GPU cluster resource allocation and bulk Token production system for mainstream LLMs including Llama, Qwen, GPT series. Optimized computing cost and token consumption rules, helped over 120 global clients cut their AI running expense by 35%~45%. Responsible for API docking, private LLM deployment and customized token quota solution design.

Microsoft

AI Technical Consultant

Microsoft • Temps plein

Apr 2023 - Apr 20241 yr

Provided one-on-one consultation for global AI startups & individual developers, including GPU model selection, computing budget calculation, token pricing planning and LLM interface access guidance. Completed more than 40 lightweight AI resource architecture optimization projects.