Software Development Engineer – AI/ML Networking Disaggregated Inference

Job overview

Compensation is $165,000–$223,000 per year. The Software Development Engineer – AI/ML Networking Disaggregated Inference role is an onsite position based in Cupertino, CA. 00 - 223,600.00 USD annually, and this role supports the Annapurna Labs team within AWS, focusing on high-performance networking for AI infrastructure. This role exists to build and optimize low-level software for high-speed data movement across AI accelerators. It contributes to the team's goal of minimizing latency and maximizing throughput for large-scale machine learning models by pushing hardware performance to its theoretical limits.

What you'll do

• Build and optimize low-level data-movement software for KV cache and activations
• profile real workloads to identify and resolve performance bottlenecks
• work across the stack from network transport to inference frameworks
• deliver features for large-scale AI clusters.

What we're looking for

Skills & competencies

full-time

day shift

cupertino ca

annapurna labs

software engineer

ai/ml

networking

c++

linux

performance optimization

$165k-$223k

Work arrangement

• Weekend coverage required

Benefits & perks

• Health insurance, 401(k) matching, paid time off, parental leave, sign-on payments, and restricted stock units (RSUs).

Why this role

Focus on disaggregated inference and high-performance networking for AI/ML infrastructure.

About the employer

Annapurna Labs (U.S.) Inc. is hiring for this role. Industry: Custom Computer Programming Services. Sector: 54.