jobholds

PhD Intern - AI Accelerator Programming and Testing

الولايات المتحدة • تاريخ النشر: 2022-01-13 • 7 مشاهدة

تفاصيل ومتطلبات الوظيفة

Pacific Northwest National Laboratory (PNNL) is a world-class research institution powered by a highly educated, diverse workforce committed to the values of Integrity, Creativity, Collaboration, Impact, and Courage. Every year, scores of dynamic, driven people come to PNNL to work with renowned researchers on meaningful science, innovations and outcomes for the U.S. Department of Energy and other sponsors; here is your chance to be one of them! At PNNL, you will find an exciting research environment and excellent benefits including health insurance, flexible work schedules and telework options. PNNL is located in eastern Washington State—the dry side of Washington known for its stellar outdoor recreation and affordable cost of living. The Lab’s campus is only a 45-minute flight (or ~3 hour drive) from Seattle or Portland, and is serviced by the convenient PSC airport, connected to 8 major hubs. Overview The development and testing of advanced problem-solving methods based on High Performance Computing (HPC) and Machine Learning (ML) now face many serious productivity crises brought about by the increased use of heterogeneity such as GPUs, throwing today’s software testing methods for HPC off-track. In response, the Pacific Northwest National Laboratory is exploring novel testing methods that not only help restore order but stay relevant despite the continued growth of heterogeneity. We are looking at a self-motivated Ph.D. intern researcher with a strong background in GPU and AI/ML/RL accelerator programming and/or testing. The candidate will be expected to collaborate closely with laboratory personnel in computing and application domains, as well as researchers at collaborating national laboratories, universities, and industry on project activities focused on heterogenous platform evaluation, and GPU-based scientific computing/ML program validation. Responsibilities Responsibilities and Accountabilities include: Assisting scientists to evaluate the numeric precision and performance of emerging accelerators, such as GPU Tensorcores, TPUs, and other CGRA/FPGA based accelerators. Investigating and tackling the challenges of porting traditional scientific applications to the emerging heterogenous platforms, using non-traditional floating-pointe format. Assisting in the delopment of profiling, instrumentation and monitoring tools based on the LLVM compiler infrastructure and/or NVBit for numeric error detection & recovery in GPU-based HPC/ML applications. Qualifications Candidates must be currently enrolled/matriculated in a PhD program at an accredited college. Minimum GPA of 3.0 is required. Preferred Qualifications: Expertise in floating-point format, such as FP16 and other AI-based floating point formats; expertise in numerical error analysis and/or Uncertainty Quantification; expertise with open-source compiler frameworks such as LLVM; experience with AI accelerator evaluation, including architectures such as those from SambaNova, Cerebras, Nvidia, Google Hazardous Working Conditions/Environment Not applicable Additional Information Not applicable Testing Designated Position Not applicable Commitment to Excellence, Diversity, Equity, Inclusion, and Equal Employment Opportunity Our laboratory is committed to a diverse and inclusive work environment dedicated to solving critical challenges in fundamental sciences, national security, and energy resiliency. We are proud to be an Equal Employment Opportunity and Affirmative Action employer. In support of this commitment, we encourage people of all racial/ethnic identities, women, veterans, and individuals with disabilities to apply for employment. Pacific Northwest National Laboratory considers all applicants for employment without regard to race, religion, color, sex (including pregnancy, sexual orientation, and gender identity), national origin, age, disability, genetic information (including family medical history), protected veteran status, and any other status or characteristic protected by federal, state, and/or local laws. We are committed to providing reasonable accommodations for individuals with disabilities and disabled veterans in our job application procedures and in employment. If you need assistance or an accommodation due to a disability, contact us at [email protected]. Drug Free Workplace PNNL is committed to a drug-free workplace supported by Workplace Substance Abuse Program (WSAP) and complies with federal laws prohibiting the possession and use of illegal drugs. Mandatory Requirements Battelle requires employees to have a COVID-19 vaccine as a condition of employment, subject to accommodation. Applicants are required to disclose their vaccination status following a conditional offer of employment and must attest to being fully vaccinated with a Center for Disease Control (CDC)-approved COVID-19 vaccination, or provide documentation of need for medical or religious exemption from the COVID-19 vaccination requirement.
شارك هذه الوظيفة مع زملائك ومجموعاتك:

ملخص الوظيفة

المجال / التصنيف تكنولوجيا المعلومات
الدولة الولايات المتحدة
نوع الدوام دوام كامل
إعلان وظيفة موثوق ومعتمد تم التحقق من بيانات الإعلان لضمان تجربة تقديم آمنة ومباشرة للباحثين عن عمل.