Systems Performance Engineer, AI Solutions Lab - Santa Clara, CA, United States

Originally posted 16 October 2026 by the employer.

This role focuses on performance optimization across AI serving and training stacks using leading models and customer-relevant configurations.

About the role

This role involves driving end-to-end performance optimization across AI serving and training stacks, identifying bottlenecks across the full data path, and developing benchmark methodologies. You will work within the AI Solutions Lab to validate Marvell's AI platform portfolio, including Teralynx network fabrics, integrated optical platforms, and emerging memory fabric products.

What you'll do

• Drive end-to-end performance optimization across AI serving and training stacks.
• Identify bottlenecks across the full data path, from application request flow through compute, memory, communication layers, GPU kernels, network transport, and data/storage pipelines.
• Develop and execute benchmark methodologies that are reproducible, technically credible, and relevant to customer use cases.
• Profile serving-stack internals — quantization, scheduling, KV-cache management, and disaggregated prefill/decode — to identify concrete optimization targets.
• Analyze results and develop performance narratives that guide kernel, runtime, communication, and system-level optimizations.
• Create performance summaries, visuals, and benchmark artifacts for customer presentations, executive reviews, and trade-show demonstrations.

What you'll need

• Experience with AI serving frameworks such as vLLM, SGLang, TensorRT-LLM, or similar platforms.
• Strong background in RCCL/NCCL, RDMA, communication-compute overlap, and performance profiling.
• Hands-on experience with GPU profiling tools (e.g., Nsight Systems/Compute, PyTorch Profiler, or ROCm Compute Profiler) to localize bottlenecks at the kernel level.
• Demonstrated ability to diagnose end-to-end bottlenecks across application, framework, runtime, and infrastructure layers.
• Working knowledge of at least one distributed training framework (PyTorch DDP/FSDP, DeepSpeed, or Megatron-LM).
• Strong Python and Linux skills.
• Comfortable working in containerized environments (Docker; Kubernetes a plus) to ensure benchmark reproducibility.

Nice to have

• Experience benchmarking distributed large-model inference and training systems.
• Familiarity with GPU kernel analysis, system tracing, and workload-specific optimization.
• Familiarity with serving-stack internals such as continuous batching, paged KV-cache attention, and quantization techniques (e.g., GPTQ, SmoothQuant).
• Exposure to customer proofs of concept, competitive benchmarking, or externally consumed performance reporting.
• Go experience is a plus.
• Kubernetes experience is a plus.
• Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related field; a PhD is a plus.

Skills: AI serving and training stacks, GPU profiling tools, distributed training framework, Python, Linux