Sr Software Development Engineer, Neuron

Salary: $193,500 - 193,500 per year Requirements:

• Bachelors degree in computer science or an equivalent field
• 5+ years of experience building complex software systems that have been successfully delivered to customers
• 5+ years of experience contributing to the architecture and design of new and existing systems, including architecture patterns, reliability, and scaling
• Masters degree in computer science or an equivalent field
• Familiarity with collective communication methods such as all-reduce and all-gather, or with distributed training frameworks

• Improve collective algorithms and topology choices to maximize training performance
• Use Neuron Explorer and similar tools to pinpoint bottlenecks in compute and bus bandwidth usage
• Track and interpret processor, DMA, firmware, and workload metrics
• Tune collective operations so AI compute scales efficiently across the data center
• Partner closely with our hardware team to co-optimize software and Trainium silicon
• Develop and refine C/C++ implementations of collective communication patterns
• Examine and implement enhancements for the training topologies used by modern LLMs
• Create and sustain analysis frameworks and automation solutions

• AI
• AWS
• EC2
• Firmware
• Hardware
• Support
• Cloud
• Flow
• Machine Learning

More:

We are Annapurna Labs, part of AWS, and we build the hardware and software foundations that support EC2 infrastructure. Our Trainium and Neuron Collectives teams focus on purpose-built AI training technology that helps frontier AI models scale across thousands of chips. We work at the intersection of hardware, firmware, and distributed systems, with a strong emphasis on inclusion, work-life balance, mentorship, and career growth. We also offer flexible working hours, comprehensive benefits, paid time off, parental leave, and a compensation package that may include sign-on payments and RSUs. This role is based in Cupertino, California.

last updated 37 week of 2026