Senior Staff Engineer, Performance Modeling

Please Note:

To provide the best candidate experience with our high application volumes, we limit applications to a total of 10 over 6 months. 

Advancing the World’s Technology Together
Our technology solutions power the tools you use every day--including smartphones, electric vehicles, hyperscale data centers, IoT devices, and so much more. Here, you’ll have an opportunity to be part of a global leader whose innovative designs are pushing the boundaries of what’s possible and powering the future. 

We believe innovation and growth are driven by an inclusive culture and a diverse workforce. We’re dedicated to empowering people to be their true selves. Together, we’re building a better tomorrow for our employees, customers, partners, and communities.

What You’ll Do

The APL (Advanced Processor Lab) is one of the research team's of SAIT (Samsung Advanced Institute of Technology) which is Samsung‘s R&D hub, established as the incubator for cutting-edge technologies. SAIT’s mission has covered various research areas from AI applications/algorithms research, neuromorphic processor, domain-specific accelerators to new materials, quantum computing, and super computer system.

APL is committed to shaping the future of CPU processor and SoC architecture for the most demanding applications of the future like AI and HPC. We are building the foundation of processors and the related platform which are applied to various business targets of Samsung in the future. 

We are seeking a highly experienced CPU Performance Modeling Engineer to join our CPU architecture team. The ideal candidate will have 8+ years of experience in performance modeling and simulation for CPU designs. This role involves developing and refining detailed performance models, analyzing CPU performance characteristics, and working closely with micro architects to optimize next-generation CPU designs. You will be instrumental in driving performance improvements and ensuring that our CPU architectures meet power, performance, and area (PPA) targets.

Location: Hybrid, working onsite at our San Jose office 3 days per week, with the flexibility to work remotely the remainder of your time

Job ID: 42313

• Develop and maintain performance models for CPU cores using cycle-accurate simulation environments.
• Collaborate with CPU architects and micro architects to define and refine CPU performance goals and metrics.
• Analyze CPU performance bottlenecks and work closely with the design team to implement optimizations.
• Model various CPU components, including instruction fetch, decode, execution pipelines, caches, and memory subsystems.
• Conduct detailed performance evaluations for both single-core and multi-core architectures.
• Investigate and model new microarchitectural features and their impact on overall CPU performance.
• Use performance models to perform trade-off analysis of different architectural choices, including power and area considerations.
•  Provide performance projections, validate the models against RTL simulations, and propose improvements based on findings.
• Collaborate with compiler, software, and verification engineers to ensure design performance is aligned across all layers of development.

.

What You Bring

• Bachelors in Electrical/Computer Engineer with 15 years of relevant industry experience, or Masters in Electrical/Computer Engineer with 13 years or PhD in Electrical/Computer Engineer with 8 years preferred.
• 8+ years of experience in CPU/GPU/DSP/AI/NoC performance modeling and simulation.
• Expertise in building and using cycle-accurate performance models for CPU and SoC architectures.
•  Strong understanding of microarchitecture, including pipelines, out-of-order execution, branch prediction, cache hierarchy, and memory subsystems.
• Proficiency in using performance modeling tools and simulators (e.g., gem5, Sniper, or custom modeling tools).
• Solid understanding of CPU instruction sets (e.g., x86, ARM, RISC-V) and their impact on performance.
• Hands-on experience in C/C++, SystemC programming and scripting languages such as Python, Perl, or TCL for model development and automation.
• Experience analyzing performance using trace-driven simulation, benchmarking, and performance counters.
• Familiarity with power and area modeling, and unde