Job Board

GigaIO provides disruptive interconnect technology to extend PCIe outside the server and across racks  to achieve game-changing performance, scalability, and composability for Advanced Scale Computing  used in AI/ML/DL, advanced analytics, and high-performance computing. The Fabrex™ PCIe Switch  interconnect breaks the server boundary to connect dozens to hundreds of heterogeneous compute  engines (CPUs, GPUs, FPGAs, ASICs), memory pools, and NVMe storage devices (SSDs) into dynamically  composable, high-performance computing systems. 

AI-ML Performance Graduate Intern 

We are seeking a graduate-level intern to evaluate configuration recipes for deploying Fabrex™ network  products in the context of a variety of AI-ML use cases. This person will propose, construct, and  evaluate complete customer solutions, characterize the performance of GigaIO’s disruptive Fabrex™  interconnect compared with the performance of legacy solutions, and document reference  configurations (recipes) and performance results. This person will report to the VP of Engineering during  the period of the internship. He/she will apply his/her expertise with AI-ML use cases, applications, and  benchmarks in a variety of market segments. The term of the internship is negotiable and may extend  to continued employment, based on mutual desire. 

Must Haves: 

1) Broad understanding of multiple tiers of systems software; applications, middleware, OS  libraries, OS Kernel, OS Drivers. 

2) Background in performance analysis and familiarity with a variety of standard AI-ML performance benchmarks (e.g., MLPerf, BERT, ResNet, MLBench, etc.) 

3) Familiarity with AI-ML programming using CUDA, multi-GPU NCCL, PyTorch, TensorFlow. 4) Strong scripting skill (Python, Perl, or a Linux shell). 

5) C programming skill. 

6) Thorough, focused, methodical, with good documentation habits 

7) Excellent conversational, written communication, and presentation skills, in English. 

Wants: 

1) Experience with a network product or system, preferably at the switch level. 2) General knowledge of a variety of interconnect protocols (e.g., PCI-e, InfiniBand, NFS, TCP/IP,  and Ethernet) 

3) Familiarity with HPC programming including MPI and Libfabric. 

Education Requirements: 

1) BS and currently working toward MS or PhD in computer science, computer engineering,  electronics engineering, mathematics, physics, or similar field. 

Send responses to roneill@gigaio.com

6108 Avenida Encinas # B Carlsbad, CA 92011 www.gigaio.com 




The position, based in San Diego, is to be filled as soon as possible with a contract period of 2 years, with the option of extension.

The Automatic Implementation of Secure Silicon (AISS) program (https://www.darpa.mil/program/automaticimplementation-of-secure-silicon), funded by the Defense Advanced Research Projects Agency (DARPA), aims to ease the burden of designing secure chips. To achieve this goal, one research thrust of the program focuses on automatic generation, integration and optimization of System-on-Chips (SoCs). UC San Diego and Purdue University, part of a team led by Synopsys, Inc. which also includes ARM, Inc., are researching automatic design of domain-specific SoCs with a focus on machine learning as the application domain.

The post-doctoral position will work with Professor Sujit Dey at UCSD and Professor Anand Raghunathan at Purdue University, leading a team of graduate students working on developing methodologies and tools for fast and scalable Multi-Objective (PASS: Power-Area-Speed-Security) Estimation and Optimization, enabling fast and automated mapping of neural network applications to PASS-optimized hardware-software architectures. The position will also coordinate with sponsors, coordinate the deliverables including reports, presentations and software code. Salary will be commensurate with experience.

Minimum Qualifications

  • PhD in CS/CSE/ECE
  • Solid background in hardware-software design for embedded systems and ASICs, and/or system-level EDA
  • Solid understanding of machine learning and neural networks
  • Strong research capabilities, demonstrated through a track record of publications in competitive journals or conferences
  • Highly self-motivated and committed, with flexibility as well as the ability to work in and contribute to a team.

Optional Qualifications

  • Experience in implementing neural networks in hardware-software architectures
  • Experience with machine learning frameworks like TensorFlow and Pytorch
  • Experience with large scale software development

Qualified candidates are requested to submit their application including:

  • CV,
  • Brief statement describing your research experience and interests,
  • Official transcript of coursework and grades

by email as a single PDF document using reference in Subject: Post Doc-AISS-UCSD-Purdue, to Theresa Lachman tlachman@eng.ucsd.edu.

Campus Information

The University of California, San Diego is an Equal Opportunity/Affirmative Action Employer advancing inclusive excellence. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, covered veteran status, or other protected categories covered by the UC nondiscrimination policy.

 

San Diego, CA