The role involves building and optimizing low-level data-movement software for transferring KV cache and activations across accelerators and servers. The team, part of Annapurna Labs at AWS, focuses on high-performance networking solutions for AI and HPC workloads. Engineers will work closely with hardware and software experts to enhance the performance of large language models. This position offers opportunities for mentorship and career growth in a fast-paced, innovative environment.

• Strong C/C++ programming skills with a genuine interest in low-level, performance-critical systems.
• Solid command of Linux, memory management, and writing fast code.
• Experience with high-speed networking, HPC interconnects, or GPU/accelerator systems is a strong plus.
• 3+ years of non-internship professional software development experience.
• Bachelor's degree in computer science or equivalent.

• Build and optimize low-level data-movement software for transferring KV cache and activations.
• Profile real workloads to identify bottlenecks and improve performance.
• Work across the stack from network transport to inference frameworks.
• Deliver features for large clusters serving significant AI models in production.
• Collaborate with infrastructure experts, hardware engineers, and scientists.

• Employees at Amazon are often offered comprehensive health benefits—including multiple medical plan options (no pre-existing condition exclusions, 100% covered in-network preventive care), dental and vision plans, a 24/7 medical advice line from day one, expert second-opinion services, and broad mental-health support with several free counseling sessions (including pediatric). Financial wellness typically includes a 401(k) with company match (up to 2%), Restricted Stock Units (equity), FSAs, an emergency savings program, product and partner discounts, and even college-savings and home-purchase programs. Overall, the package is designed to support employees and their families’ health, finances, and day-to-day life.