NIM Solution Architect
@ NVIDIA

Beijing, Beijing, China
$150,000
On Site
Full Time
Posted 6 hours ago

Your Application Journey

Personalized Resume
Apply
Email Hiring Manager
Interview

Email Hiring Manager

XXXXXXXXXX XXXXXXXXXXX XXXXXX******* @nvidia.com
Recommended after applying

Job Details

About NVIDIA

NVIDIA is a leading company in AI computing, HPC, Visual Computing, and Gaming. With an innovative team, NVIDIA is driving advanced technologies that bring next-generation solutions to various industries.

The Role - NIM Solution Architect

This role involves leveraging NVIDIA's cutting-edge technology to design AI computing platforms, optimize large models, create AI workflows, and deliver technical support to customers.

What You’ll Be Doing

  • Drive the implementation and deployment of NVIDIA Inference Microservice (NIM) solutions.
  • Use the NIM Factory Pipeline to package optimized models into containers for on-prem or cloud deployment.
  • Refine NIM tools and support the community in building performant NIMs.
  • Design and implement agentic AI tailored to customer business scenarios.
  • Deliver technical projects, demos, and client support tasks.
  • Provide technical support and guidance to facilitate adoption of NVIDIA technologies.
  • Collaborate with cross-functional teams to expand AI solutions.
  • Champion NVIDIA software solutions within the technical community.
  • Act as an industry thought leader integrating NVIDIA inference services.
  • Support NVAIE team operations and business in China.

What We Need To See

  • 3+ years of relevant experience with a Bachelor’s or Master’s in Computer Science, AI, or related field.
  • Proven experience in deploying and optimizing large language models.
  • Proficiency in inference frameworks like TensorRT, ONNX Runtime, or PyTorch.
  • Strong programming skills in Python or C++.
  • Familiarity with mainstream inference engines such as vLLM or SGLang.
  • Experience with DevOps/MLOps tools such as Docker, Git, and CI/CD practices.
  • Excellent problem-solving and troubleshooting skills.
  • Demonstrated ability to collaborate effectively across diverse, global teams.

Ways To Stand Out From The Crowd

  • Experience in architectural design for field LLM projects.
  • Expertise in model optimization techniques, especially with TensorRT.
  • Knowledge of AI workflow design and cluster resource management tools.
  • Familiarity with agile development methodologies.
  • CUDA optimization experience and expertise in deploying large-scale HPC systems.

Key skills/competency

  • NVIDIA
  • AI
  • HPC
  • Inference
  • Python
  • C++
  • Docker
  • TensorRT
  • CI/CD
  • DevOps
Apply without a personalized resume

How to Get Hired at NVIDIA

🎯 Tips for Getting Hired

  • Customize your resume: Tailor skills and experiences to NVIDIA's needs.
  • Highlight technical expertise: Showcase AI and inference experience clearly.
  • Research NVIDIA's culture: Understand their focus on AI and HPC.
  • Prepare technical demos: Be ready to discuss past project implementations.

📝 Interview Preparation Advice

Technical Preparation

Review TensorRT and inference frameworks.
Practice Python and C++ coding challenges.
Familiarize with Docker and CI/CD pipelines.
Study containerization and model packaging techniques.

Behavioral Questions

Describe past cross-team collaboration.
Explain your problem-solving approach.
Discuss handling technical project challenges.
Share experience with client support tasks.

Frequently Asked Questions