Postdoctoral Fellow for Advanced Optical Interconnects in Datacenters

Berkeley Lab - California - The (CAG) is interested in the design, architecture and programming of future HPC systems to enable continued scientific research. A timely question for our group is how to prepare future HPC and data center systems given the expectation of many heterogeneous computing resources, and the continued need for higher performance efficiency to reach the next milestone after exascale computing. CAG is investigating related topics as well, such as specialized hardware accelerators, micro-architectural enhancements, new devices to replace existing CMOS transistors, emerging memories, 3D, and photonics. These challenges have motivated the research in the Photonic Integrated Networked Energy efficient datacenter (PINE) project. The PINE architecture addresses the data movement challenge by leveraging the unique properties of photonics to steer bandwidth to where it is needed rather than over-provisioning network resources, which significantly increases energy consumption. Photonics can also be used to efficiently perform resource disaggregation which includes advanced photonic link technology, Photonic Multichip modules, and optical circuit switches to dynamically reconfigure/aggregate resources to meet the needs of diverse workloads. We are seeking a Postdoctoral Fellow for Advanced Optical Interconnects in Datacenters to participate primarily in system-level architectural studies using models of emerging photonic components. In particular, the focus of this position is to design novel ways for resource disaggregation and network reconfiguration at every level (node to system) to best serve HPC and datacenter applications and take advantage of the unique strengths of optical switches and links. This project requires expertise in networks and computer architecture. The successful candidate will also have opportunities to participate in exciting projects in related fields, such as in micro-architectural research towards improving performance of critical HPC and datacenter applications. We value and strive for diversity in backgrounds, experiences, and perspectives. What You Will Do: Design and implement a multi-scale modeling and simulation environment to model the impact of a wide range of ideas in computer networks and architecture. Capture communication and computation traces from important HPC and datacenter applications using CPUs and GPUs to guide this study. Work closely with the developers of emerging optical components such as switches for incorporation into the simulation framework, including developers of other relevant technologies. Provide feedback and suggestions to those developers on how to improve their components to better fit HPC and data center systems. Use demonstrated expertise in networks and computer architecture to design a novel approach to resource disaggregation and network reconfiguration in all system levels that includes the reconfiguration algorithm, physical topology limitations, topology construction, routing, adapting to different optimization goals, impact to the applications, etc. Collaborate with algorithm and software developers for the purpose of making results of research easily accessible to them. Participate in all requested assignments, including research, preparation of funding proposals, documentation of results and reporting results to sponsors. Establish research directions and pursue funding opportunities. What is Required: PhD in Computer Science, Applied Mathematics, Computational Science, Mechanical Engineering, Physics or a related discipline. Understanding of devices and their models, 3D integration, emerging memory technologies, and architecture specialization (e.g., accelerators). Demonstrated expertise in working with modeling and simulation methods and software tools for hardware exploration. Demonstrated expertise in setting research direction and priorities for future computing architectures or network architectures. Demonstrated expertise in Verilog, C++, Python. Familiarity with HPC and datacenter applications. Excellent verbal and written communication skills. Demonstrated ability to work effectively as part of a cross-disciplinary team. Desired Qualifications: Demonstrated expertise in photonic systems. Demonstrated expertise in HPC or datacenter applications. Demonstrated expertise in Scala. Understanding of programming models popular in HPC and datacenters. For full consideration, please apply by October 29, 2020. Notes: This is a full-time 2 year, postdoctoral appointment with the possibility of renewal based upon satisfactory job performance, continuing availability of funds and ongoing operational needs. You must have less than 3 years of paid postdoctoral experience. Salary for Postdoctoral positions depends on years of experience post-degree. This position is represented by a union for collective bargaining purposes. Salary will be predetermined based on postdoctoral step rates. This position may be subject to a background check. Any convictions will be evaluated to determine if they directly relate to the responsibilities and requirements of the position. Having a conviction history will not automatically disqualify an applicant from being considered for employment. Work will be primarily performed at Lawrence Berkeley National Lab, 1 Cyclotron Road, Berkeley, CA. Equal Employment Opportunity: Berkeley Lab is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status. Berkeley Lab is in compliance with the Pay Transparency Nondiscrimination Provision under 41 CFR 60-1.4. Click to view the poster and supplement: "Equal Employment Opportunity is the Law." Lawrence Berkeley National Laboratory encourages applications from women, minorities, veterans, and other underrepresented groups presently considering scientific research careers.... - Permanent - Full-time

source http://jobviewtrack.com/en-in/job-1e1c417d42171b0a4817540c1a000247234518040604287b525e5900000d531b5202044121171149170905717a444e59490b0c1a4806410f6a2e1e130c4315046b354f4751425a655c5917/4ca898956392497d0d4cc84cc9a6474c.html?affid=f584d43114bf1954a48e3ec6be21b6ec