Full-Time
Posted on 9/4/2024
Optimizes deep learning inference workloads
Mid
Austin, TX, USA + 1 more
More locations: Mountain View, CA, USA
Hybrid role requiring in-office presence 3-5 days a week in Mountain View, CA or Austin, TX.
Codeium provides a service that optimizes deep learning inference workloads for businesses using AI applications. The service enhances the performance of these applications by addressing common bottlenecks in CPU, I/O, and network, which can hinder the effective use of GPU hardware. Codeium achieves this by relocating GPU code to remote resources that are highly utilized, while keeping the core logic on more affordable CPU instances. This approach can lead to significant improvements in resource utilization and cost savings, sometimes up to tenfold. Clients can register their deep learning models with Codeium, which then optimizes their performance, making it a trusted solution for demanding applications like large-scale autonomous vehicle simulation. The goal of Codeium is to improve the efficiency and cost-effectiveness of deep learning applications for its clients.
Company Stage
Series C
Total Funding
$236.4M
Headquarters
San Jose, California
Founded
2021
Help us improve and share your feedback! Did you find this helpful?