Principal Product Manager, Augmented Memory Grid

Job not on LinkedIn

🔥 0 minutes ago

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

WEKA

WebsiteLinkedInAll Job Openings

201 - 500 employees

Founded 2013

🤖 Artificial Intelligence

🏢 Enterprise

🤝 B2B

💰 $140M Series E - WEKA on 2024-05

Artificial Intelligence • Enterprise • B2B

WEKA is an enterprise-focused company that provides an "AI-Native Data Platform." The available materials reference a WEKA support portal used for customer access and account management, indicating the company offers platform software and support for AI/data workloads aimed at business customers.

📋 Description

• Own the AMG product roadmap, including KV-cache/prefix-cache offload, memory tiering, and integrations with inference engines and orchestration layers. • 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. • Work with enterprise customers and GPU cloud partners to gather requirements, validate benchmarks, and prioritize features that reduce cost-per-token and improve SLAs. • Partner with NVIDIA and other silicon/inference-stack partners on joint roadmap and certification work. • Define and track TTFT, throughput, and cache-hit-rate benchmarks demonstrating AMG’s value. • Support sales and field teams with technical positioning, competitive differentiation, and enterprise deal support.

🎯 Requirements

• Hands-on product or engineering experience with LLM inference serving, including vLLM, NVIDIA Triton/TensorRT-LLM/NIM, Ray Serve, or comparable systems • Fluency in KV-cache, prefix/context caching, quantization, and batching strategies • Working knowledge of modern production LLM serving, including context windows, multi-tenant serving, and GPU scheduling • Fundamentals of high-performance networking and distributed systems, including RDMA, GPUDirect Storage, NVMe-oF, or equivalent • Track record working directly with large enterprise accounts, including requirements gathering, production deployments, and SLAs • 10+ years of product management experience, ideally partly in infrastructure, ML platforms, or developer-facing technical products • Strong leadership skills and experience leading cross-functional teams • Ability to influence without authority • Strategic product thinking and ability to translate goals into actionable plans • Excellent communication and interpersonal skills • Ability to explain complex technical concepts to technical and non-technical stakeholders • Nice-to-have: experience at a GPU cloud, inference platform, or AI infrastructure startup • Nice-to-have: familiarity with storage systems in AI/ML pipelines • Nice-to-have: experience partnering with NVIDIA or other accelerator/silicon vendors

🏖️ Benefits

• Equal opportunity employment • Diverse, inclusive and authentic workplace • No discrimination or harassment based on protected characteristics