Principal Product Manager, Augmented Memory Grid (AMG)

10 hours, 37 minutes ago
Lead
Product Management
WEKA

WEKA

WEKA provides a cutting-edge data platform for cloud and on-premises data management, offering WekaFS for high-performance storage solutions in data-intensive environments.

IT Services
201-500
Founded 2014
$294M raised

Description

  • Own the AMG product roadmap, including KV-cache and prefix-cache offload, memory tiering, and inference-serving integrations.
  • Partner with engineering to define architecture trade-offs across GPU memory, high-performance networking, and distributed storage.
  • Translate inference performance bottlenecks such as time-to-first-token, throughput, and context length into product requirements.
  • Gather requirements, validate benchmarks, and prioritize features with enterprise customers and GPU cloud partners running production inference workloads.
  • Partner with NVIDIA and other silicon and inference-stack providers on joint roadmaps and certification efforts.
  • Define and track benchmarks, including time-to-first-token, throughput, and cache-hit rate, to demonstrate AMG value.
  • Support sales and field teams with technical positioning, competitive differentiation, and enterprise deal support.
  • Present product strategy and roadmaps to internal stakeholders and external customers.

Requirements

  • 10+ years of product management experience, ideally including infrastructure, ML platforms, or developer-facing technical products.
  • Hands-on product or engineering experience with LLM inference serving, such as vLLM, NVIDIA Triton, TensorRT-LLM, NIM, Ray Serve, or comparable platforms.
  • Fluency in KV-cache, prefix/context caching, quantization, and batching strategies.
  • Working knowledge of production LLM serving, including context windows, multi-tenant serving, and GPU scheduling.
  • Knowledge of high-performance networking and distributed-systems technologies such as RDMA, GPUDirect Storage, and NVMe-oF.
  • Experience translating model-level constraints and inference performance needs into infrastructure requirements.
  • Track record working directly with large enterprise customers on requirements gathering, production deployments, and SLAs.
  • Strong cross-functional leadership, strategic planning, and ability to influence without authority.
  • Ability to communicate complex technical concepts to technical and non-technical stakeholders.
  • Experience at a GPU cloud, inference platform, or AI infrastructure startup; familiarity with AI/ML storage systems; and experience partnering with NVIDIA or other accelerator vendors (preferred).

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Sr. Product Manager -Senior Living

PointClickCare 1001-5000 Health Care Providers & Services

PointClickCare is seeking a Senior Product Manager to lead strategy and delivery for senior living workflows that improve resident care across its healthcare technology platform.

Agile Azure Scrum
7 hours, 37 minutes ago

Sr. Product Manager -Senior Living

PointClickCare 1001-5000 Health Care Providers & Services

PointClickCare is seeking a remote Senior Product Manager to lead strategy, development, and delivery of Senior Living platform workflows that improve resident care and enable AI-powered care delivery.

Agile Azure Scrum UX Design
7 hours, 37 minutes ago

Director, AI Transformation

TTEC Digital 1001-5000 Professional Services

Lead TTEC Digital’s internal AI transformation program, turning business workflows into scalable, governed AI solutions that deliver measurable enterprise impact.

Generative AI
7 hours, 37 minutes ago

Product Management Director, Supplier Network (AI-Powered)- 11969

Coupa Software 1001-5000 Internet Software & Services

Coupa is seeking a Product Management Director to lead AI-powered strategy and growth for its global Supplier Network, improving buyer-supplier connections, trust, monetization, and marketplace liquidity.

Generative AI Machine Learning
7 hours, 37 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers