Software Development Engineer – AI/ML Networking Disaggregated Inference, Annapurna Labs , Elastic Collectives

What you’d do

Build and optimize low-level data-movement software that transfers KV cache and activations across accelerators, servers, and heterogeneous memory over AWS's high-performance network fabric. Profile real workloads, find bottlenecks, and work across the stack from network transport up to inference frameworks. Full-time. Found on the employer's careers page on Oct 2, 2026. Apply through the link.

You’ll need

• Strong C/C++
• Low-level, performance-critical systems experience
• Linux and memory management
• Performance profiling and optimization