לוח משרות דרושים, לחיפוש זה נמצאו 31,450 משרות

The MLIL DataPlane team is looking for a Software Development Engineer to own the design and implementation of our inference data plane. We build the software that makes large models run efficiently on custom hardware - spanning model execution, memory management, data movement, and serving integration.
Our work covers the full inference path: integrating serving engines with custom hardware, developing high-performance compute kernels, enabling efficient data movement, and driving models from early validation through production. We operate at frontier scale with large distributed models.
This is a ground-up effort with rapidly evolving hardware and software. We are looking for an IC who can write and optimize low-level code for custom hardware, validate model architectures end-to-end, build test and profiling infrastructure, and drive performance across the stack.

Key job responsibilities
- Develop and optimize compute kernels for a custom ML accelerator architecture, targeting production-level performance for large language model inference.
- Implement and validate LLM architectures (decoder-only, mixture-of-experts) end-to-end - from PyTorch model definition through distributed execution on custom hardware.
- Integrate custom accelerator backends into open-source ML serving frameworks (vLLM, PyTorch), including scheduler extensions, memory management, and model parallelism.
- Build and maintain test infrastructure for model correctness validation across CPU, GPU, simulator, and hardware targets.
- Profile and optimize inference workloads - identify bottlenecks, instrument critical paths, and drive latency and throughput improvements from simulation through hardware bringup.
- Own features end-to-end: from design through implementation, testing, and integration into the broader software stack.
- Contribute to CI/CD pipelines that gate model and kernel changes on correctness and performance regressions.

We are seeking an experienced engineer to join our team that owns the network stack for EC2 distributed AI/ML systems. The team develops support for a variety of frameworks and communication libraries including NCCL, NVSHMEM, NIXL, NCCL GIN, and Perplexity kernels. Solid knowledge of Linux, networking, and performant coding is important. Experience with embedded systems is valued, and experience with high-speed networking or HPC/RDMA interconnects is highly valued.

If you like solving hard problems, want to work with HPC and ML customers, iterate fast and deliver meaningful solutions at scale, then come join us! This truly is a role at the forefront of AI/ML-you'll be working on features for the largest clusters, with the largest customers, for the largest AI models.

Key job responsibilities
Be a senior engineer on a team that builds and maintains the infrastructure that monitors and reports on functionality and performance of massive testing workloads run at scale. Use our internal CI/CD tools, Linux, and public AWS products to automate the delivery of our software to customers, saving developer time. Write Python code that effortlessly spools up large clusters and runs benchmarks and applications for ML and HPC workloads. Use AWS Managed Grafana and Athena to digest the massive amount of performance data generated by these workloads and create dashboards for developers and stakeholders. Invent automatic mechanisms to alert developers to functional and performance regressions so they never reach reach customers. Manage the complexity of infrastructure that covers many instance types, software stacks, Linux operating systems, cutting-edge releases and make it easy to evolve.