Staff Engineer, Compiler

Samsung Electronics•Austin, TX

3d•$151,000 - $226,600

About The Position

Samsung, a world leader in advanced semiconductor technology, is founded on a simple philosophy – the endless pursuit of excellence will create a better world for all. At Samsung Austin Research and Development Center (SARC) and Advanced Computing Lab (ACL), we are building a center of excellence for Intellectual Property (IP) that is applied to high-performance computing devices (mobile, automotive, and other custom market segments) consumed by millions of people around the world. Come build with us! Role and Responsibilities The Samsung Software Team for Xclipse GPU is responsible for the following areas: User Mode Driver (UMD) Development; Kernel Mode Driver (KMD) / System Software Development; Compiler Development; GPU Compute / Machine Learning on the Edge; Next-Gen GPU Software / Hardware codesign; Post-Silicon Performance Optimization / Workload analysis; Game Engine feature integration; and Software Validation and Automation. As a Staff Engineer, you will use your broad expertise and unique knowledge to develop GPU IP from the early Architectural planning process until we productize and ship millions of devices to consumers. You will be responsible for becoming a domain expert in one or more project areas, and gaining knowledge and competencies for developing new features and debugging any customer issues related to your domain. you will also have the opportunity to mentor junior engineers and interns, and work with other departments for cross team-initiatives. You have advanced-level Software Development in C/C++/Python You will design and implement features for compiler targeting Samsung GPU architecture from OpenGL-ES and OpenCL applications. You will apply best practices using git, gerrit (code reviews), continuous integration You will debug compiler failures and performance issues using code and graphics debugging tools You will be working with the driver team to integrate compiler into driver infrastructure and determining compilation strategies for good performance and low power usage You will provide senior level documentation and communication using common project management tools (JIRA, Confluence, Wiki, Chat, Email)

Requirements

6+ years of experience with a Bachelor's Degree in Computer Science, Computer Engineering, or comparable field, or 4+ years of experience with a Master’s Degree, or 2+ years of experience with a Ph.D.
6+ years of experience in one of the following areas: register allocation, instruction scheduling, graphics-specific optimizations, SIMD relevant control flow and code placement optimizations, classic machine independent optimizations, preferably on low-level IRs
6+ years of experience in software engineering using C, C++, and scripting languages (e.g., Python, Bash).
6+ years of object-oriented and component-based design experience
Excellent problem-solving skills, with the ability to analyze complex issues and develop creative solutions.
Strong communication and collaboration skills, with experience working with cross-functional global teams and external partners.

Responsibilities

Develop GPU IP from the early Architectural planning process until we productize and ship millions of devices to consumers.
Becoming a domain expert in one or more project areas, and gaining knowledge and competencies for developing new features and debugging any customer issues related to your domain.
Mentor junior engineers and interns, and work with other departments for cross team-initiatives.
Design and implement features for compiler targeting Samsung GPU architecture from OpenGL-ES and OpenCL applications.
Apply best practices using git, gerrit (code reviews), continuous integration
Debug compiler failures and performance issues using code and graphics debugging tools
Work with the driver team to integrate compiler into driver infrastructure and determining compilation strategies for good performance and low power usage
Provide senior level documentation and communication using common project management tools (JIRA, Confluence, Wiki, Chat, Email)