drjobs MLHPC GPU Performance Architect - 46

MLHPC GPU Performance Architect - 46

Employer Active

1 Vacancy
drjobs

Job Alert

You will be updated with latest job alerts via email
Valid email field required
Send jobs
Send me jobs like this
drjobs

Job Alert

You will be updated with latest job alerts via email

Valid email field required
Send jobs
Job Location drjobs

Austin - USA

Monthly Salary drjobs

Not Disclosed

drjobs

Salary Not Disclosed

Vacancy

1 Vacancy

Job Description


What you do at AMD changes everything

At AMD we push the boundaries of what is possible. We believe in changing the world for the better by driving innovation in highperformance computing graphics and visualization technologies building blocks for gaming immersive platforms and the data center.

Developing great technology takes more than talent: it takes amazing people who understand collaboration respect and who will go the extra mile to achieve unthinkable results. It takes people who have the passion and desire to disrupt the status quo push boundaries deliver innovation and change the world. If you have this type of passion we invite you to take a look at the opportunities available to come join our team.

HPC/ML GPU Performance Architect:

AMD is looking for an outstanding technical contributor & lead to help optimize performance of AMD basednextgeneration GPU accelerators for HPC and Machine Learning. As a passionate and dedicatedServer GPU Performance Architect in the MI SOC ArchitectureTeam you will optimize SOCperformance by identifying opportunities across all parts of system architecture spanning theapplication and related frameworks driver GPU core memory & I/O subsystems. You will collect andanalyze performance profiling data andtraces to isolate performance bottlenecks and share theinsights to help drive features into the next generation of server GPUs and software stack components. The ideal candidate is expected to be well informed on latest trends in GPU accelerated HPC and MLandbe able to quickly ascertain in a datadriven manner how next generation server GPUs andplatforms should be engineered to support those needs.

Key Responsibilities:

Establishes and maintains AMDs technological leadership position

Considered technical leader across project and departmental boundaries and has a proventrack record for sustained innovation.

Is responsible for projects or processes of significant strategic or commercial importance and for project/program results

Deals with problems requiring cutting edge approaches and champions innovation across theorganization

Makes technical decisions that have a significant impact on product families go to marketstrategies and customer satisfaction

Has business and technical time horizon of generally 6 to 36 months.

Accountability on project with significant influence on project/product timetomarketschedules.

Provides consultative direction with senior management

Coaches and mentors experienced staff

Represents AMD to the outside technical community partners and vendors

Work closely with other team members to understand design architecture and to proposesolutions to improve/enhance performance with given SoC/IP and markets.

Architectural modeling performance triage deeper analysis identifying bottlenecks workingwith architects and proposing solutions for performance improvement.

Developing tools and methodology for performance modeling workloads analysis.

Proposing communicating and implementing solutions to issues.

Lead technical teams participate and present in executive reviews on product planning andexecution.

Participate in collaborative development and workload performance optimization with AMDspartners/customers.

Position Requirements:

Exceptional foundation in systems architecture cutting across CPU or GPU memory storageand I/O subsystems

Power user of performance profiling tools

Experience with hardware performance counter monitoring tools

Knowledge of OS internals and kernel parameter tuning experience

Exposure to GPU accelerator performance benchmarks and codes are a plus (HPL HPCG STREAM MLPerf HACC QMCPACK LAMMPS etc.

Excellent communication skills (verbal written and presentation)

> 7 years relevant industry experience

Education Requirements:

Masters degree required PhD preferred emphasis in Electrical or Computer Engineering Computer

Architecture or Computer Science with SoC/IP performance studies.

      • AMD is a government contractor and subcontractor. As required by Executive Order our US employees are required to be fully vaccinated against COVID19 regardless of the employees work location or work arrangement (e.g. telework remote work etc. subject to such exceptions as required by law. If selected you will be required to be vaccinated against COVID19 and submit documentation of proof of vaccination by January 4 2022. AMD will provide additional information regarding what information or documentation will be needed and how you can request an exception from this requirement if you have a need for a religious and/or medical accommodation.


Requisition Number:124246
Country:United StatesState:TexasCity:Austin
Job Function:Design

AMD does not accept unsolicited resumes from headhunters recruitment agencies or fee based recruitment services. AMD and its subsidiaries are equal opportunity employers. We consider candidates regardless of 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. Please click here for more information.

Employment Type

Full-Time

About Company

Report This Job
Disclaimer: Drjobpro.com is only a platform that connects job seekers and employers. Applicants are advised to conduct their own independent research into the credentials of the prospective employer.We always make certain that our clients do not endorse any request for money payments, thus we advise against sharing any personal or bank-related information with any third party. If you suspect fraud or malpractice, please contact us via contact us page.