SoC Architect, Media, Computer vision and Neural Engine

Lab Overview:

The Samsung SOC Lab creates high performance SoC architecture for various Galaxy device lineups. This lab collaborates with Samsung's strategic SoC partners, Samsung MX headquarter team, and key R&D teams around the globe to innovate and reinvent technology that will positively impact millions of people around the world via the Galaxy flagship products.

Position Summary:

We are looking for a SOC Architect to lead architecture of Media, Computer Vision and Neural engine in next generation SOCs. This is a highly visible hands-on role technical leadership role.

Position Responsibilities:

• Guide on development of innovative Computer vision and Neural Engine Architectural and microarchitectural features to boost KPIs (Key Performance Indicators) on various targeted workloads in next generation SOCs
• Innovate, create and deliver Media, Computer Vision and Neural Engine architecture proposals for products in new and existing markets
• Evaluate architecture proposal benefits in collaboration with team of SoC Architects and communicate the results across related engineering audiences (SW, HW, Architecture, Leadership)
• Perform high-level performance modeling/simulation and analysis of Media, Computer Vision and Neural Engine features, applications, benchmarks, and complex uses cases
• Create performance models and studies to support inclusion of these features in the next generation SoC architecture based on performance, area or power improvement
• Collaborate with workload characterization to verify and debug the proposal and its delivered performance

Required Skills:

• BSc, Masters or PhD in Computer Science/Engineering, or equivalent combination of education, training, and experience
• 10+ years of experience in SOC or ASIC RTL design
• Prior direct experience (> 7 years) in hardware architecture or RTL design is required
• High proficiency in architecture analysis and performance modeling, ranging from simple analytical models to complex cycle accurate performance model and correlation, especially around Computer vision and Neural Engine
• Ability to leverage existing simulation capabilities [GEM5, FastSIM, VisualSim] or create new simulation capabilities when necessary
• Detailed knowledge of ARM bus infrastructure (ACE/AXI/AHB), existing and emerging Media, Computer Vision and Neural Engine
• Leadership across hardware, software, and platform groups to align all parties to a common vision