CPLD/FPGA Firmware Engineer, Annapurna Labs, ML Accelerator Systems Firmware

Annapurna Labs, a cutting-edge division of Amazon Web Services (AWS), is seeking an experienced CPLD/FPGA Firmware Engineer to join their ML Acceleration Server Firmware team. This role sits at the intersection of hardware and software development, focusing on creating high-performance Machine Learning servers from conception to deployment.

The position involves developing firmware for power sequencing and control systems in ML Acceleration servers within data center environments. You'll work with various technologies including computer architecture, hardware description languages (HDLs), and embedded systems, using languages such as Verilog, C, C++, Lua, bash, and Python.

As a member of this team, you'll be responsible for implementing power sequencing and managing various protocols including PWM, I2C, and SPI. The role requires expertise in developing systems software, kernel drivers, and building comprehensive test automation flows. You'll work in a highly cross-functional environment, collaborating with both software and hardware teams to optimize customer experience.

The position offers the opportunity to work on scalable designs that can be tested throughout different stages of product development, including manufacturing and production. You'll leverage automation, continuous integration, and fleet metrics to deploy and monitor your changes effectively.

AWS provides a supportive environment focused on work-life harmony, with flexible working culture and numerous opportunities for professional growth. The company values diversity and inclusion, demonstrated through employee-led affinity groups and ongoing learning experiences like Conversations on Race and Ethnicity (CORE) and AmazeCon conferences.

This role is particularly suited for those interested in system programming related to accelerators and devices, focusing more on device drivers than training algorithms. While the team works with machine learning workloads for system validation, the primary focus is on co-developing reliable server software and hardware for customers to deploy their ML workloads at scale.

Join a team that's pushing the boundaries of hardware/software co-design and help build the infrastructure that powers the future of machine learning computation at scale.