Senior Staff Engineer, SoC NPU Architect
About this role
The Samsung SoC Architecture Lab builds innovative system-on-chip architectures, key IP blocks, and memory subsystems for future Galaxy smartphones, IoT devices, and flagship products. Individuals stepping into this senior position will lead hands-on NPU sub-system architecture development, performance modeling, interface design, and hardware-software co-optimization to shape next-generation mobile technology. The team exists to drive high-performance architecture development in collaboration with global research groups and strategic partners, directly impacting millions of users worldwide. Someone who thrives here brings extensive technical background in neural processing unit development, strong analytical problem-solving skills, and the capability to communicate complex architectural proposals effectively across diverse engineering teams.
What you will do
- Propose innovative neural processing unit architectural and micro-architectural features to enhance performance, power, and area metrics on targeted workloads.
- Conduct high-level performance modeling, simulation, and analysis covering applications, benchmarks, and complex use cases.
- Develop cycle-accurate and analytical performance models while correlating results with silicon implementation.
- Deliver detailed architecture and microarchitecture proposals and specifications to design teams and technology leadership.
- Analyze benchmarks, application workloads, and simulation results to drive continuous optimizations.
- Map artificial intelligence use cases to the processor and co-design hardware and software for low power and high performance.
- Collaborate across system, driver, and operating system teams to bring architecture proposals to fruition.
What you need
- Possess a bachelor’s, master’s, or PhD degree in electrical engineering, computer science, a related science, or equivalent combination of education, training, and experience.
- Bring fourteen or more years of professional experience in neural processing unit architecture and development.
- Demonstrate hands-on experience in developing cycle-accurate performance and functional models.
- Exhibit solid knowledge and practical application of convolutional neural networks and large language models.
- Maintain proficient programming skills utilizing Python, SystemC, or C++.
- Accumulate prior work experience involving machine learning frameworks such as TensorFlow, PyTorch, or ONNX.
- Show familiarity with the microarchitecture of systems-on-chip, interface subsystems, and logic modules.
Nice to have
- Experience in performance and power modeling using Platform Architect
- Experience in mapping AI use cases to IPs
- Experience with hardware memory management units, prefetching, or memory subsystems
- Experience with multi-core systems and memory coherency
- Experience in ML model optimization on GPU architecture
Benefits
- Annual bonus eligibility
- Comprehensive compensation package with generous benefits
Skills and tech stack
Questions candidates ask
What is the salary range for this role?
The base pay range for roles at this level is $203,700 to $305,500 USD. Individual rates depend on factors including the role’s function, location, and the individual’s knowledge, skills, experience, education, and training.
Where is the position located?
The position is located at 665 Clyde Avenue, Mountain View, CA, USA, and will be performed in an office setting.
What background is required for this position?
Candidates need a bachelor’s, master’s, or PhD degree in electrical engineering, computer science, a related science, or equivalent combination of education, training, and experience. In addition, applicants must have 14+ years of experience in neural processing unit architecture and development.
The application is on the official Samsung Research America careers page.
Apply on company site