> Markdown version of [/jobs/ext/1656853-senior-software-engineering-manager-kv-cache-platform](https://www.wearedevelopers.com/jobs/ext/1656853-senior-software-engineering-manager-kv-cache-platform). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Senior Software Engineering Manager - KV Cache Platform - **Company:** DataDirect Networks - **Location:** San Francisco, CA, United States (Remote available) - **Experience:** Expert - **Salary:** $220,000.0 - $275,000.0 - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Software Bug Management, C++ (Programming Language), Cloud Computing, Cloud Engineering, Computer Clusters, Program Optimization, Software Quality, Computer Programming, Linux, Distributed Data Store, Distributed Systems, Python (Programming Language), Remote Direct Memory Access, Release Management, Distributed Caching, Software Deployment, Software Engineering, AI Infrastructure, Large Language Models, Kubernetes, TensorRT - **Published:** July 10, 2026 - **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/17537652?backUrl=%2Fcareer%2F17537652%2FSenior-Software-Engineering-Manager-Kv-Cache-Platform-California-San-Francisco ## About the Role * 15+ years of experience building distributed systems, cloud infrastructure, storage platforms, or AI infrastructure software. * 7+ years leading high-performing software engineering organizations, including geographically distributed teams. * Proven experience delivering large-scale distributed infrastructure products from architecture through production deployment. * Strong background in distributed systems, Linux, networking, performance engineering, and cloud-native architectures. * Hands-on programming experience with Go and Python; experience with C/C++ is a plus. * Demonstrated ability to lead cross-functional initiatives and influence technical direction across multiple organizations. * Experience building AI infrastructure, LLM serving platforms, distributed caching systems, or high-performance storage solutions. * Experience with technologies such as NVIDIA Dynamo, TensorRT-LLM, Triton, RDMA, GPUDirect Storage, BlueField DPUs, Kubernetes, or related AI infrastructure. * Background in HPC, distributed storage, networking, or enterprise infrastructure software. * Experience working directly with strategic customers, technology partners, OEMs, or hyperscalers to deliver enterprise AI solutions. ## Description DDN is seeking a Senior Software Engineering Manager to lead the engineering organization responsible for our KV Cache Platform-a distributed memory and storage platform that accelerates large-scale LLM inference across GPU clusters. In this role, you will lead geographically distributed engineering teams responsible for building highly scalable, low-latency distributed systems that power AI inference. You will define the technical vision and execution strategy for the platform while partnering closely with Product Management, Sales, Customer Engineering, NVIDIA, and executive leadership to deliver innovative AI infrastructure that meets customer needs and supports DDN's long-term product strategy. This is a highly visible leadership role with responsibility for engineering execution, customer success, roadmap delivery, and building a world-class engineering organization. Responsibilities Lead, mentor, and grow a geographically distributed team of software engineers and technical leaders, fostering a culture of technical excellence, innovation, ownership, and collaboration. * Define and execute the technical strategy and roadmap for the KV Cache Platform, ensuring scalability, reliability, security, and operational excellence. * Drive the architecture, development, and delivery of distributed systems supporting AI inference, GPU memory optimization, distributed caching, RDMA networking, GPUDirect Storage, NVIDIA BlueField DPUs, and emerging AI infrastructure technologies. * Partner closely with Product Management, Sales, Customer Engineering, NVIDIA, and strategic technology partners to prioritize customer requirements, drive proof-of-concepts (POCs), influence product direction, and successfully deliver customer deployments. * Own day-to-day engineering execution, including feature development, release planning, bug triage, production issues, customer escalations, and cross-functional execution to ensure timely, high-quality software delivery. * Establish engineering best practices for software quality, observability, automation, performance, testing, and production readiness. * Collaborate across engineering, infrastructure, and hardware teams to deliver scalable, production-ready AI infrastructure while developing future engineering leaders and driving continuous improvement. ## Related Videos - [Shipping Faster with Less: Render on Cloud Hosting, AI Workloads, and the Future of DevOps](https://www.wearedevelopers.com/videos/1894-shipping-faster-with-less-render-on-cloud-hosting-ai-workloads-and-the-future-of-devops) - [Understanding Kubernetes in a visual way](https://www.wearedevelopers.com/videos/100085-understanding-kubernetes-in-a-visual-way) - [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/videos/100099-tour-de-force-open-source-llm-inference-optimization-from-simple-to-sophisticated) - [Docker network without Docker](https://www.wearedevelopers.com/videos/1418-docker-network-without-docker) - [Instant KAI Sandboxes with vCluster: Multi-Tenant, Multi-Scheduler GPU Sharing](https://www.wearedevelopers.com/videos/100333-instant-kai-sandboxes-with-vcluster-multi-tenant-multi-scheduler-gpu-sharing) - [Efficient deployment and inference of GPU-accelerated LLMs​](https://www.wearedevelopers.com/videos/929-efficient-deployment-and-inference-of-gpu-accelerated-llms) ## Related Articles - [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers) - [Best US AI Conferences for CTOs in 2026: Build vs. Buy, Vendor Evaluation, and Peer Intelligence](https://www.wearedevelopers.com/magazine/736-best-us-ai-conferences-for-ctos-in-2026-build-vs-buy-vendor-evaluation-and-peer-intelligence) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix) - [How to Turn Community Events Into a Powerful AI GTM Engine: The Daytona Playbook](https://www.wearedevelopers.com/magazine/732-how-to-turn-community-events-into-a-powerful-ai-gtm-engine-the-daytona-playbook)