Simplify Logo

Full-Time

Advanced Packaging Lead

Posted on 6/18/2024

Untether AI

Untether AI

51-200 employees

Enhances AI inference with at-memory computing

Hardware
AI & Machine Learning

Senior

Remote in Canada

Category
Hardware Engineering
Electronic Hardware Engineering
Requirements
  • Experience working with 2.5/3D packaging technologies using CoWoS, EMIB or similar
  • Experience with chiplets, die-to-die interconnects and designs with stacked memories
  • Experience with manufacturing processes, reliability and qualification of advanced packaging designs through production ramp
  • Working knowledge of package design tools and failure analysis
  • Demonstrated success with designs in advanced technology nodes
Responsibilities
  • Develop advanced packaging solutions for next generation AI products
  • Collaborate with internal stakeholders, product, architecture and design to analyze and propose packaging solutions to improve performance, reliability and manufacturability
  • Drive technical decisions, short-term and long-term, on packaging solutions, chiplet strategy and die-to-die interfaces
  • Manage and collaborate with external suppliers, foundry and OSAT to propose leading-edge packaging solutions
  • Review electrical, thermal, mechanical and feasibility data from suppliers and lead analysis through high volume production
  • Resolve quality and integrity issues related to package design
  • Drive long term plans to grow internal capabilities and expertise in these areas

Untether AI enhances the speed and efficiency of AI inference workloads using at-memory computing. This method places the compute element next to memory cells, which boosts compute density and accelerates AI inference for various neural networks, such as those used in vision, natural language processing, and recommendation systems. The company targets businesses that rely on AI technologies and need high-performance computing for inference tasks. Their products, including the runAI200® devices and tsunAImi® accelerator cards, are designed to deliver exceptional performance, with the tsunAImi® card offering over 2 PetaOps. This allows businesses to process AI workloads more effectively within a compact power envelope. Untether AI's goal is to provide efficient and cost-effective solutions for companies looking to optimize their AI applications.

Company Stage

Series B

Total Funding

$165M

Headquarters

Toronto, Canada

Founded

2018

Growth & Insights
Headcount

6 month growth

7%

1 year growth

10%

2 year growth

16%
Simplify Jobs

Simplify's Take

What believers are saying

  • Untether AI's recent $20 million funding round and total funding of over $200 million CAD indicate strong financial backing and growth potential.
  • The appointment of industry veterans like Chris Walker as CEO and Renxin Xia as VP of Hardware Engineering brings experienced leadership to drive innovation and market expansion.
  • The release of the imAIgine SDK version 22.12 enhances developer velocity, making it easier and faster to deploy neural networks on Untether AI's hardware.

What critics are saying

  • The highly competitive AI hardware market requires continuous innovation to maintain a technological edge.
  • Dependence on hardware sales could be a vulnerability if market demand shifts or new, more efficient technologies emerge.

What makes Untether AI unique

  • Untether AI's at-memory computing architecture significantly enhances compute density and efficiency, setting it apart from traditional AI inference solutions.
  • The company's tsunAImi® accelerator cards deliver over 2 PetaOps per card, offering unparalleled performance in a PCI-Express form factor.
  • Collaborations with industry giants like Arm and J-Squared Technologies highlight Untether AI's commitment to integrating cutting-edge technology into diverse applications, from automotive to defense.

Help us improve and share your feedback! Did you find this helpful?

INACTIVE