Senior Deep Learning Solution Architect

NVIDIA
China
Workplace: OnsiteFull timeFunction: Solutions Engineering & Sales EngineeringExperience: 5+ yearsEducation: mastersSkills: ["Learning agility","Adaptability","Problem analysis","Independent technical exploration","Performance optimization mindset"]

Build and optimize AI computing platform components focused on LLM inference and training acceleration, including distributed training compute performance and data transfer optimization. Develop open-source inference frameworks (SGLang, vLLM) with feature/operator work and performance tuning, and create KV cache offloading solutions across CPU, SSD, and remote storage. Study ML system bottlenecks and produce example code, acceleration libraries, or frameworks to improve performance efficiency.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
NVIDIA
NVIDIA
2 weeks ago

Senior Deep Learning Solution Architect

✓ Verified Job

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

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live
Reposted: similar role first listed 1 hour ago

Job Summary

Build and optimize AI computing platform components focused on LLM inference and training acceleration, including distributed training compute performance and data transfer optimization. Develop open-source inference frameworks (SGLang, vLLM) with feature/operator work and performance tuning, and create KV cache offloading solutions across CPU, SSD, and remote storage. Study ML system bottlenecks and produce example code, acceleration libraries, or frameworks to improve performance efficiency.
Location: China
Workplace: Onsite
Employment Type: Full time
Job Function: Solutions Engineering & Sales Engineering
Seniority: Mid level

Key Responsibilities

  • •Develop and contribute to open-source inference frameworks such as SGLang and vLLM, including feature/operator development, performance optimization, and model support.
  • •Develop and optimize KV cache offloading frameworks for LLM workloads, supporting multi-level cache offloading and reuse across CPU, SSD, and remote storage.
  • •Drive R&D on compute performance in distributed training and explore methods for performance optimization.
  • •Analyze computational challenges and bottlenecks in machine learning systems, then build example code and acceleration libraries/frameworks accordingly.
  • •Identify common needs in ML systems and create tooling/framework components to address performance and efficiency gaps.

Key Requirements

  • •Over 5 years of technology industry experience, with a master’s degree or above in computer science, mathematics, electrical engineering, automation, or a related field.
  • •Strong interest in accelerated computing, parallel computing, and heterogeneous computing, with motivation to explore in depth.
  • •Solid programming skills with a strong understanding of data structures and computer systems fundamentals.
  • •Strong learning agility and the ability to analyze, define, and independently explore technical problems.
  • •Familiarity with heterogeneous computing, distributed training, or parallel computing, plus experience in performance analysis/modeling/optimization is a plus.
Experience:5+ yearsAI computingHPCMachine learningLLMDistributed trainingOpen source
Education:Master's in computer science, mathematics, electrical engineering, automation, or related fields
Skills:Learning agilityAdaptabilityProblem analysisIndependent technical explorationPerformance optimization mindset
Tech Stack:SGLangVLLMKV cache offloadingFlexKVLLM inferenceLLM trainingDistributed trainingHeterogeneous 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
Glassdoor: 4.3
WebsiteLinkedInGlassdoor