高通
GPU Performance Engineer – AI Workload Focus
GPU Performance Engineer – AI Workload Focus
发布于 大约 11 小时前普通员工/个人贡献者
Hsinchu City, Hsinchu City, Taiwan
中级经验
全职员工
仅现场办公
本科
GPU
Cross-Functional Collaboration
Performance Optimization
Testing
Driver Development
AI 估算 · 28k–45k
Based on Qualcomm's global compensation and Taiwan tech market, the role commands competitive salary for AI/GPU expertise.
职位详情
关于这个职位
This position focuses on optimizing GPU performance for AI workloads at Qualcomm. You will work on AI core architecture, functional modeling, and driver/compiler development for GPU products. Collaborate with cross-functional teams to ensure advanced performance and power goals.
最低要求
Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 4+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience. OR Master's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 3+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience. OR PhD in Computer Engineering, Computer Science, Electrical Engineering, or related field and 2+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.
工作职责
Leverages advanced AI knowledge and experience to architect, design, implement, verify, and/or optimize the performance and power of AI cores.
Builds functional model simulations, develops software, and tests for various AI models to verify correctness and ensures advanced performance and power goals are met.
Designs, programs, and runs comprehensive graphics tests using tools and methods under different scenarios and benchmarks to verify functionality, performance, power, and stability and identify issues.
Collaborates with cross-functional teams, third-party vendors, and external users to guide implementation and ensure alignment with needs and goals.
Develops critical driver and compiler software to support GPU products.
Writes detailed technical documentation and feature descriptions for complex AI projects to guide users and/or customers to implement output.
优先资格
Master's degree or PhD in Computer Engineering, Computer Science, Electrical Engineering, or related field. 2+ years of relevant AI/CPU/NPU/GPU experience. 1+ year of work experience in a role requiring interaction with senior leadership (e.g., Director and above). 1+ year in a technical leadership role with direct reports (only applies to positions with direct reports).
AI 洞察
优缺点分析
优点
- Work on cutting-edge AI and GPU technology at a global leader.
- Opportunity to make significant impact on next-gen products.
- Competitive compensation and benefits typical for top tech firms.
- Strong career growth in high-demand AI hardware field.
- High technical complexity and constant learning required.
- Potential for tight project deadlines and high expectations.
- Limited work-from-home flexibility based on job nature.
- Engineers passionate about AI and GPU performance, who thrive in a technically demanding environment and enjoy cross-functional collaboration.
缺点 / 挑战
暂无明显挑战项
角色解读
- Progress to senior GPU architect or technical lead.
- Move into management roles overseeing AI/GPU teams.
- Become a domain expert in AI hardware acceleration across the industry.
- Architect and optimize performance and power of AI cores for GPU products.
- Build functional model simulations and develop software to verify AI model correctness.
- Develop critical driver and compiler software to support GPU products.
- Collaborate with cross-functional teams and external vendors to align implementation.
- Deep understanding of AI/GPU architecture and performance optimization.
- Proficiency in functional modeling, simulation, and testing.
- Experience with driver and compiler development.
- Strong cross-functional collaboration and communication skills.
申请策略
- Study Qualcomm's GPU and AI product lines to align your experience.
- Prepare to discuss specific examples of performance optimization you achieved.
- Be ready for technical interviews covering architecture, algorithms, and system design.
- Emphasize projects involving AI model optimization, GPU programming, or performance analysis.
- Detail experience with functional modeling, simulation tools, and driver/compiler development.
- Showcase cross-functional teamwork and leadership in technical roles.
- Highlight any publications or patents related to AI hardware.
- Deepen knowledge of GPU architecture (e.g., NVIDIA CUDA, AMD ROCm) and AI accelerators.
面试指南
- Use the STAR method for behavioral questions: Situation, Task, Action, Result.
- For technical problems, start with problem scope, then propose multiple solutions with trade-offs.
- Show systematic thinking: define metrics, measure baseline, identify bottlenecks, implement optimizations.
- How would you optimize the performance of a deep learning inference on a GPU?
- Describe a time you improved the power efficiency of a hardware accelerator.
- What is the role of a compiler in GPU performance?
- How do you approach cross-functional collaboration with different teams?
- Explain your method for debugging a performance issue in a GPU driver.
匹配度报告
76
综合匹配度
High-impact AI/GPU role at a global tech leader with excellent development prospects but limited flexibility.
适合人群
This role is ideal for candidates who prioritize cutting-edge technical growth and career advancement over flexible work arrangements.
最强匹配
成长发展匹配
最弱匹配
工作生活匹配
薪资福利85
成长发展90
工作生活60
使命价值70
薪资福利匹配
85较高
Qualcomm is a top-paying company with strong benefits culture. Although specific figures are not mentioned, the role likely commands a high salary and good perks.
薪资信号未披露（AI估算：28K-45K/月）
成长发展匹配
90较高
The role involves cutting-edge AI and GPU technologies, offering excellent skill development and career growth in a high-demand field.
技术前沿前沿/新兴技术
技术栈GPU、AI、Performance Optimization
业务类型profit_center
工作生活匹配
60中等
The position is site-based at Hsinchu Science Park with no mention of remote or flexible hours. Work-life balance is typical for a hardware engineering role.
工作模式仅现场办公
办公地点科技园/产业园
加班情况未提及（无法判断）
使命价值匹配
70中等
Working at a tech leader like Qualcomm contributes to advancing global connectivity and AI, but the direct social impact is moderate.
行业发展高速增长赛道
社会影响中性/一般
创新程度积极采用新技术
Watch Jobs