Company:

Qualcomm China

Job Area:

Engineering Group, Engineering Group > Software Engineering

General Summary:

Job Overview

Responsible for neural network development in the automotive domain, focusing on automotive neural network functionality, developing cutting-edge ADAS and GenAI features, and holistically improving performance and accuracy using HW awareness development and optimization concept on Qualcomm Snapdragon Ride platforms, and further strengthen Qualcomm AI echo system.

This role also emphasizes deployment and optimization of Large Language Model (LLM) and/or Vision Language Model (VLM) that support next generation intelligent automotive systems.

Enhancing existing system level solutions and creating new architecture based on the latest and greatest neural networks emerging from the research community and optimizing them for Snapdragon next generation system and platforms.

Minimum Qualifications

We are looking for experts in self-discipline and continuous learning with knowledge-based qualifications:

1+ years C/C++ and Python programming experience on Linux or other embedded system

Familiar with popular deep learning frameworks, especially Pytorch and TensorFlow.

Good at software development with excellent analytical, development, and problem-solving skills.

Hands-on experience with deep learning network design and implementation

Understanding mathematics in DL/ML can solve practical problems.

Practical knowledge for NN training, including but not limited to dataset augmentation, training tech, issue triage, and evaluation report.

Experience working with LLMs or multi‑modal models (VLM/VLA), including fine‑tuning, optimization, or deployment.

Excellent communication skills in both Chinese and English (verbal, presentation, written)

Ability to collaborate across a globally diverse team.

Preferred Qualifications

Deep familiarity with modern high performance LLM inference frameworks

• vLLM (continuous batching, PagedAttention, speculative decoding integration)
• llama.cpp / GGMLfamily runtimes (quantization, CPU/GPU backends, memory efficient graph execution) ‑family runtimes‑efficient graph execution)
• SGLang (query planning, parallel decode engines, dynamic graph optimization)
• TensorRT‑Edge-LLM, ONNX Runtime GenAI, QNN, or similar inference engines for latency‑sensitive deployments
  
  
  

LLM Inference Acceleration Expertise, Including But Not Limited To:

• Speculative Decoding, EAGLE, MTP, and related multi‑token prediction techniques
• KV Cache management, reuse policies, hierarchical coaching, eviction strategies
• Advanced attention optimizations such as continuous batching, PagedAttention, SparseAttention, Flash‑Attention variants
• Experience profiling and optimizing memory bandwidth, and runtime scheduling
  
  
  

Multi‑modal / VLA Integration Experience, Including:

• Combining text‑vision, text‑sensor, or text‑action models
• Building multi‑modal reasoning for robotics or autonomous driving (perception → language → action loops)
• Experience adapting open‑source VLM/VLA models (LLaVA, Qwen‑VL, InternVL, OpenVLA, etc.) to embedded or ADAS workflows
  
  
  

Published/Accepted paper in high-ranking conferences, e.g. CVPR/ICCV/ECCV is a plus.

Minimum Qualifications:

• Bachelor's degree in Engineering, Information Systems, Computer Science, or related field.
  
  
  

Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail disability-accomodations@qualcomm.com or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).

Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.

To all Staffing and Recruiting Agencies: Our Careers Site is only for individuals seeking a job at Qualcomm. Staffing and recruiting agencies and individuals being represented by an agency are not authorized to use this site or to submit profiles, applications or resumes, and any such submissions will be considered unsolicited. Qualcomm does not accept unsolicited resumes or applications from agencies. Please do not forward resumes to our jobs alias, Qualcomm employees or any other company location. Qualcomm is not responsible for any fees related to unsolicited resumes/applications.

If you would like more information about this role, please contact Qualcomm Careers.