NVIDIA

3 months ago

Solutions Architect - Physical AI TPM

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Lead architectural design for AI computing platforms focused on LLM inference and distributed training acceleration. Contribute to open-source inference frameworks (SGLang, vLLM), develop KV cache offloading (FlexKV), optimize performance for multi-node HPC environments, and prototype acceleration libraries to solve ML system bottlenecks. Work with global teams across research and engineering to deliver scalable, cutting-edge AI solutions.

Location: Beijing

Workplace: Onsite

Employment Type: Full time · Permanent

Job Function: Solutions Engineering & Sales Engineering

Key Responsibilities

•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.

Key Requirements

•Over 10 years of experience in the technology industry, with a master's degree or above in computer science, mathematics, electrical engineering, automation, or related fields.
•Strong interest in accelerated computing, parallel computing, and heterogeneous computing, with the motivation to explore these areas in depth.
•Solid programming skills, with a good understanding of data structures and computer systems fundamentals.
•Strong learning agility, adaptability, and the ability to analyze, define, and independently explore technical problems.
•Familiarity with heterogeneous computing, distributed training, or HPC is a plus.

Experience:10+ yearsAIHPCHigh-performance computingLLMDistributed training

Education:Master's in Computer scienceUnknown

Skills:SGLangVLLMKV cacheFlexKVDistributed trainingHPC

Tech Stack:SGLangVLLMKV cacheFlexKVDistributed trainingHPCHigh-performance computingAI computing

Company Brief

NVIDIA

Designs and manufactures GPUs, AI accelerators, and system-on-chip products for gaming, data centers, professional visualization, and automotive markets, enabling advanced graphics, AI, and high-performance computing solutions worldwide.

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1993

Glassdoor: 4.3

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

NVIDIA

3 months ago

Solutions Architect - Physical AI TPM

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Location: Beijing

Workplace: Onsite

Employment Type: Full time · Permanent

Job Function: Solutions Engineering & Sales Engineering

Key Responsibilities

•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.

Key Requirements

•Over 10 years of experience in the technology industry, with a master's degree or above in computer science, mathematics, electrical engineering, automation, or related fields.
•Strong interest in accelerated computing, parallel computing, and heterogeneous computing, with the motivation to explore these areas in depth.
•Solid programming skills, with a good understanding of data structures and computer systems fundamentals.
•Strong learning agility, adaptability, and the ability to analyze, define, and independently explore technical problems.
•Familiarity with heterogeneous computing, distributed training, or HPC is a plus.

Experience:10+ yearsAIHPCHigh-performance computingLLMDistributed training

Education:Master's in Computer scienceUnknown

Skills:SGLangVLLMKV cacheFlexKVDistributed trainingHPC

Tech Stack:SGLangVLLMKV cacheFlexKVDistributed trainingHPCHigh-performance computingAI computing

Company Brief

NVIDIA

Industry: Electronics Manufacturing

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Public Company

Valuation: Public Company (Market Cap in USD)

Funding: IPO / Publicly Listed

Headquarters: Santa Clara, United States

Founded: 1993

Glassdoor: 4.3

Website LinkedIn Glassdoor