Senior Software Engineering Manager – KV Cache Platform

Job 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.

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.

Qualifications

• 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.