jobs
Software Development Engineer – AI/ML Networking Disaggregated Inference, Annapurna Labs , Elastic Collectives
Every token a large language model generates depends on data reaching the right accelerator at the right moment. As AI models outgrow any single chip, the network between accelerators becomes the…
In inglese
- Company
- Amazon
- Location
- Cupertino, California, USA
- Status
- Closed
- Posted
- 2026-10-01
Annapurna Labs, part of AWS, is hiring a software engineer for its Elastic Collectives team, working on disaggregated LLM inference. The engineer builds and tunes low-level data-movement software that shifts KV cache and activations between accelerators, servers and heterogeneous memory over AWS's fastest network fabric, profiling workloads to push components toward hardware limits. The posting wants strong C/C++ and Linux systems skills; RDMA, InfiniBand, libfabric, UCX, NCCL or MPI exposure is a plus. Prior AI/ML experience is not required.
Original job posting