GPU Performance Attainment Engineer Job Listing at AMD in Orlando, FL (Job ID 64336-en-us)

Description

WHAT YOU DO AT AMD CHANGES EVERYTHING

We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences – the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world's most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives. 

AMD together we advance_

GPU Performance Attainment Engineer

THE TEAM: 

AMD's Data Center GPU organization is transforming the industry with our AI-based Graphic Processors. Our primary objective is to design exceptional products that drive the evolution of computing experiences, serving as the cornerstone for enterprise Data Centers, (AI) Artificial Intelligence, HPC and Embedded systems. If this resonates with you, come and join our Data Center GPU organization where we are building amazing AI powered products.

THE ROLE:

As a member of the pre-silicon performance attainment team, you will be a technical contributor that drives end-to-end delivery of solutions, directly contributing to, and coordinating workload optimization across multiple teams for inference and training of machine learning models. The position will involve interfacing with software and hardware engineering teams to plan, develop and optimize use cases. This is an exciting opportunity to work on the cutting edge of GPU Computing for Machine Learning.

THE PERSON:
Driven by a passion for solving real-world GPU performance challenges in datacenter environments. Thrives on hands-on problem solving in large-scale GPU deployments, with a strong focus on performance optimization and tackling complex, unsolved issues. A skilled communicator and persuasive influencer, known for strategic, critical, and analytical thinking. A collaborative team player who adapts easily and leverages collective strengths to develop innovative, impactful solutions. 

KEY RESPONSIBLITIES:

• Prepare & run tests, debug issues, and analyze results on the full-chip Emulation Platform/RTL Simulator/Architecture Roofline Models.  

• Identify technical problems, break them down, summarize multiple possible solutions, and help the team to make progress.
• Analyze model projection results and identify algorithm issues to find novel solutions for improving the accuracy of projection for different families of products, and over multiple generations.
• Automate performance execution steps wherever possible to improve productivity and propose improvements to the methodologies and processes for better efficiency.
• Get performance projections for kernels using an analytical model. Identify efficiency issues, and work with model owners to resolve performance projection shortcomings.
• Work with the workloads team to select the workload traces, run the selected workload traces on the performance simulator, analyze the performance results and metrics to root cause any anomalies.
• Coordinate with the workloads optimization team to get the updated workloads traces.
• Collaborate with simulator team to update the environment to bridge the gap between the performance numbers and the performance goals.
• Collaborate with library, compiler, driver, and hardware engineers to influence strategic decisions to achieve the highest performance for selected workloads.
• Innovate new algorithmic improvements that exploit the strengths of the hardware architecture to deliver the best possible machine learning performance.

PREFERRED EXPERIENCE:

• Strong knowledge of CPU and/or GPU architecture.
• Solid years of experience in GPU pre-silicon performance analysis and debug.
• Experience in GPGPU programming technologies and Machine Learning.
• Experience in performance modeling and simulation tools.
• Excellent knowledge of C/C++/Scripting (Python, Perl etc.).
• Experience with Shell scripts, and Verilog is a plus.
• Familiarity with application, driver, and firmware software is a plus.

ACADEMIC CREDENTIALS:

• Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, Computer Science or a closely related field.

#LI-EV1

#LI-HYBRID

Benefits offered are described:  AMD benefits at a glance.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law.   We encourage applications from all qualified candidates and will accommodate applicants' needs under the respective laws throughout all stages of the recruitment and selection process.