DESCRIPTION

Annapurna Labs builds high-performance hardware and software solutions used in AWS data centers globally. This hardware and software are then used by all customers using AWS EC2 and adjoining services.

We're looking for a software development engineer to be at the forefront of development of ML network infrastructure. Amazon EC2 Elastic Fabric Adaptor (EFA) is a fast interconnect used by customers to run HPC and ML at scale, and used to build cutting edge high-performance computing and machine learning applications.

You will be responsible for diving deep into the networking stack and optimizing network performance for ML applications. You'll also be developing features which improve performance and compatibility with newer hardware including GPUs. Most of the work done as a part of this role is open source and you will also interact with various open source communities in developing the best solution for our customers. We move fast and focus on delivering value at speed.

This individual should feel equally comfortable in server and embedded environments and enjoy deep understanding of computer architecture and Linux OS specially the networking subsystem. Prior knowledge and experience about running distributed ML models scale is also appreciated. This role will provide you with a unique opportunity to work on an intersection of open source, infrastructure and machine learning at a large scale.

BASIC QUALIFICATIONS

• B.S. Computer Science or related technical field
• 3+ years of software development experience preferably in scalable and distributed high-performance computing
• Proficiency with one or more modern programming language: C, C++, Python
• Familiar with software development, build and deployment process for software libraries
• MPI for HPC
• NCCL for GPU

PREFERRED QUALIFICATIONS

• Experience with RDMA networking subsystem
• Experience with developing on open source software
• Experience with using distributed machine learning models
• Meets/exceeds Amazon's leadership principles requirements for this role
• Meets/exceeds Amazon's functional/technical depth and complexity for this role

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.