20 hours ago
Base Salary
$174k - $262k/yr
Responsibilities
- Design, implement, and optimize collective communication library features across scale-up and scale-out networks.
- Profile, analyze, and tune distributed training and inference workloads across multi-GPU and multi-node systems.
- Own features from technical scoping and design through implementation, testing, delivery, and performance validation.
- Develop benchmarking, performance-estimation, regression-tracking, and reporting tools and infrastructure.
- Collaborate with GPU library, runtime, ROCm, framework, and open-source teams to integrate and upstream changes.
- Provide performance analysis for future networks, NICs, and hardware-software co-design decisions.
- Support customers and internal teams with load balancing, workload scheduling, and model sharding strategies.
- Mentor junior engineers through code reviews, knowledge sharing, and technical guidance.
Requirements
- Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or a bachelor’s degree with equivalent experience.
- Senior professional experience in technical software development focused on performance engineering, communication libraries, networking, GPU systems, or distributed systems.
- Strong C++ and Python proficiency with experience in performance tuning, debugging, and test design.
- Strong knowledge of collective communication libraries such as RCCL, NCCL, and MPI, plus NIC, RDMA, and scale-up and scale-out network architectures.
- Hands-on experience profiling distributed AI workloads and optimizing large-scale, multi-node compute environments.
- Experience integrating optimized compute or communication into PyTorch, JAX, vLLM, or SGLang.
- Strong technical ownership, analytical ability, cross-functional collaboration, communication, and mentoring skills.
- A PhD is preferred.
Benefits
- The role is located in Austin, Texas or San Jose, California.
- AMD benefits are referenced in the posting, with details provided through AMD benefits at a glance.
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.