Logo of Huzzle

Home

Matches

Explore

Manage

Intern, FPGA Acceleration Research

image

Samsung Semiconductor

Nov 19, 2023

Applications are closed

  • Internship
    Full-time
    Off-cycle Internship
  • Research & Development
    Data
  • San Francisco

Requirements

  • Currently pursuing Bachelor’s (+ 5 years of experience), Master’s (+3 years of experience), or Ph.D. degree (+2 years of experience) in Computer Engineering or related field
  • In-depth knowledge of computer architecture, modern processor, CPU/GPU memory management and hands on design and modeling skills in a fast paced environment.
  • Familiar with AI/ML framework and profiling method. HLS, Verilog, C/C++, Python required.
  • Past research project experience and publication record preferred.
  • You’re inclusive, adapting your style to the situation and diverse global norms of our people.
  • An avid learner, you approach challenges with curiosity and resilience, seeking data to help build understanding.
  • You’re collaborative, building relationships, humbly offering support and openly welcoming approaches.
  • Innovative and creative, you proactively explore new ideas and adapt quickly to change.

Responsibilities

  • Develop innovative solution for CXL based tiered memory device solution to address memory intensive workload like LLM training in datacenter.
  • Fully understand the requirement of ML training pipeline and partition it efficiently on heterogeneous computing CPU/GPU/accelerators.
  • Optimize data movement across memory hierarchy.
  • Create IP, Patent and publication and generate whitepapers as outcome of this internship.
  • Analyzing system performance bottleneck of emerging applications such as LLM training, KVM, IMDB.
  • Develop new technique for effective cache management scheme with CXL interface
  • Model and report the performance of the solution
  • Build prototype on state of the art FPGA with collaboration of MSL team.
  • Complete other responsibilities as assigned.
image

Samsung Semiconductor

Manufacturing & Electronics
Industry
10,001+
Employees

Mission & Purpose

Established in 1974 as a subsidiary of Samsung Electronics, we’re proud to be recognized as one of the leading chip manufacturers in the world. Using our knowledge in semiconductor technology, our ambition is to spark the imagination of device manufacturers with top-of-the-line building blocks and, through that, enrich the lives of people around the world with transformative solutions.