Position SummaryRole and Responsibilities- Perform semiconductor engineering research, design, development, and/or testing for firm products and/or devices for use in the electronic communication industry.
- Design and develop GPU architectures that meet the performance, power, and area (PPA) requirements for ML workloads.
- Collaborate with cross-functional teams, including software, system, and validation engineers to ensure seamless integration of GPU architectures with ML frameworks and applications.
- Analyze and optimize ML algorithms, including deep learning frameworks (e.g., TensorFlow, PyTorch) and neural networks, to maximize GPU performance and efficiency.
- Develop and maintain architecture models, performance models, and simulation tools to evaluate and optimize GPU designs.
- Work closely with system architects to ensure GPU architectures are optimized for system-level performance and power efficiency.
- Keep abreast of the latest advancements in ML and GPU technologies, leveraging this knowledge to drive innovation and differentiate Samsung's GPU products in the marketplace.
- Develop and maintain technical specifications, architecture documents, and design guides for GPU architectures.
- Work with other teams to ensure successful implementation of GPU architectures in Samsung's products, including SoCs, GPUs, and ASICs.
- Engage in the development of technical road maps and strategies for ML workloads.
Skills and QualificationsMinimum Requirements:
Bachelor's degree or foreign equivalent in Computer Science, Electrical Engineering, Computer Engineering, or a closely related field plus five (5) years of experience in the job offered or in a related occupation with each of the following: GPU architecture design and GPU performance modelling for AI/ML workloads; GPU architectures, including pipeline architecture, memory hierarchy, and parallel processing; programming languages, including C, C++, Python; optimization of complex systems for performance, power; architecture modeling and simulation tools (e.g., Gems, Sniper, etc.); Modelling and analyzing the performance of ML and LLM workloads and its software optimization techniques on GPU hardware.
Alternate Requirements:
Master's degree or foreign equivalent in Computer Science, Electrical Engineering, Computer Engineering, or a closely related field and Two (2) years of experience in the job offered or in a related occupation with each of the following: GPU architecture design and GPU performance modelling for AI/ML workloads; GPU architectures, including pipeline architecture, memory hierarchy, and parallel processing; programming languages, including C, C++, Python; optimization of complex systems for performance, power; architecture modeling and simulation tools (e.g., Gems, Sniper, etc.); Modelling and analyzing the performance of ML and LLM workloads and its software optimization techniques on GPU hardware.
Total RewardsAt Samsung - SARC/ACL, base pay is one part of our total compensation package and is determined within a range. This provides the opportunity to progress as you grow and develop within a role. The base pay range for this role is between $220,834.03 - $251,760.00. Your actual base pay will depend on variables that may include your education skills, qualifications, experience, and work location. This is an exempt position, which is not eligible for overtime pay under the Fair Labor Standards Act (FLSA).
Samsung employees have access to benefits including: medical, dental, vision, life insurance, 401(k), free onsite lunch, employee purchase program, tuition assistance (after 6 months), paid time off, student loan program, wellness incentives, and many more. In addition, regular full-time employees (salaried or hourly) are eligible for MBO bonus compensation, based on company, division, and individual performance.
Additionally, this role might be eligible to participate in long term incentive plan and relocation.
U.S. Export ControlThis position requires the ability to access information subject to U.S. export control restrictions. Applicants must have the ability to access export-controlled information or be eligible to receive a government authorization to access export-controlled information.
Trade SecretsBy submitting an application, you [applicant] agree[s] not to disclose to Samsung, or induce Samsung to use, any confidential or proprietary information (including trade secrets) belonging to any current or previous employer or other person or entity.
#LI-DNI
* Please visit Samsung membership to see Privacy Policy, which defaults according to your location. You can change Country/Language at the bottom of the page. If you are European Economic Resident, please click here.
