Principal Product Manager, Augmented Memory Grid (AMG)

What you'll do

• Set the AMG roadmap for cache offload, memory tiering, and integration with inference engines and serving platforms.
• Work with engineering, customers, GPU cloud partners, and silicon partners to define requirements, validate benchmarks, and prioritize features.
• Track product benchmarks and support sales and field teams with technical positioning and enterprise deals.

What they ask for

• Hands-on product or engineering experience with LLM inference serving and fluency in KV-cache, prefix/context caching, quantization, and batching.
• Working knowledge of production LLM serving, including context windows, multi-tenant serving, and GPU scheduling.
• Fluency in high-performance networking and distributed systems, such as RDMA, GPUDirect Storage, or NVMe-oF, or equivalent.
• Experience with large enterprise accounts, including requirements gathering, production deployments, and SLAs.

Nice to have

• Experience at a GPU cloud, inference platform, or AI infrastructure startup; familiarity with storage systems in AI/ML pipelines.
• Experience partnering directly with NVIDIA or other accelerator/silicon vendors.

Tools

vLLM, NVIDIA Triton, TensorRT-LLM, NIM, Ray Serve, Kubernetes, RDMA, NVMe-oF

AI focus

Product management for AI inference infrastructure, including LLM cache offload, memory tiering, serving integrations, and performance benchmarking.