Annapurna Labs designs silicon and software that accelerates innovation. Customers choose us to create cloud solutions that solve challenges that were unimaginable a short time ago—even yesterday. Our custom chips, accelerators, and software stacks enable us to take on technical challenges that have never been seen before, and deliver results that help our customers change the world.
We're looking to hire a Software Development Engineer that will:
- Develop mission-critical software that powers Annapurna Labs' next-generation machine learning platforms' interconnect (PCIe and Neuron Link)
- Collaborate with EC2 teams and manufacturing partners to ensure seamless system integration
- Drive end-to-end qualification processes for new hardware implementations
Technologies useful to this role include operating systems, Linux architecture, embedded systems, and control systems. Our team uses, C, C++, Lua, Bash, Python and other similar languages to develop device drivers, and develop automation software.
Key job responsibilities
As a member of the Annapurna Labs Machine Learning PCIe and Neuron Link engineering team, you will develop software to enable and monitor Annapurna accelerated compute servers and EC2 systems handling customer Machine Learning workloads in AWS Data Centers world wide. You will work closely with hardware engineers to bring up new boards, custom silicon devices, and servers for EC2 accelerated computing instances. You will provide inputs to architects on the development of custom silicon and system features. You will develop automated software test and deployment pipelines to ensure software quality, compatibility, and upgradeability.
A day in the life
Daily tasks range from A to Z - as long as it relates to a PCIe interface, we're on it. This includes programming on device interfaces using standard subsystems such as I2C and SPI, as well as working on software which integrates the server with EC2, for diagnostics and performance.
About the team
The Annapurna Labs Machine Learning PCIe and Neuron Link team is responsible for all aspects of the interconnect between accelerators for the custom Trainium AI servers.
Our team consists of hardware, software, and firmware engineers all working together to create innovative and scaleable solutions for the next-generation of Trainium AI servers.
