Distinguished Engineer: AI

Job Summary

ONTAP is NetApp’s flagship storage operating system. The ONTAP team drives the product strategy, roadmap, and engineering delivery for ONTAP software and systems. You are responsible for developing innovative solutions and architecture for ONTAP software and systems spanning the areas of filesystems and storage, security, networking and protocols. The solutions you architect and design will drive mission critical applications, AI infrastructure and cloud workflows for Fortune 500 companies.

We are seeking a Distinguished Engineer with unrivaled depth in AI/ML inferencing at scale and the distributed systems foundations that power it. You will architect and ship our next-generation AI infrastructure and inferencing platform serving millions of requests with uncompromising latency, throughput, and reliability requirements.

You set the technical North Star—translating high-stakes business problems into elegant, defensible architectures that teams rally behind. You drive consensus through technical authority, shaping roadmaps where your architectural decisions become company strategy. You invent solutions where standard approaches fail, and turn constraints into lasting competitive moats.

Job Responsibilities

 Provide the technology strategy to accelerate the pace of innovation within NetApp and the Industry.
Define the roadmap and long-term vision, derived from key business priorities, technology and competitive trends as well as new and emerging customer use cases.
 Partner with Product management and engineering to define and deliver next generation products for NetApp.
 Influence executive management and engineering to contribute towards a competitive portfolio. Demonstrate influence and act as a force multiplier across engineers at NetApp.
Mentor senior and principal engineers and be the technical bar-raiser for senior and principal technical roles.
Evangelize both internally and externally for NetApp products you own and become an industry recognized authority on related technologies and domain.
What will you bring:

Globally recognized as domain expert in software and system design for highly scalable distributed storage and databases, control and data plane architectures required to fuel large scale infrastructure for serving Gen AI and AI as a Service workloads.
Experience building highly resilient and scalable enterprise grade products.
Experience in building large scale, compute intensive stateful applications.
Ownership for Product and System architecture for multiple significant projects
Expertise in coding, design, architecture, subsystems, and technology trends
Excellent communication skills to communicate with executives, senior leadership on products, technology trends and customer issues.

Job Requirements

AI Inferencing & ML Systems: Deep hands-on experience with high-performance inference engines (TensorRT, vLLM, ONNX Runtime, Triton), model optimization (quantization, pruning, distillation), and serving patterns for LLMs and computer vision models at scale. Proven track record building, architecting RAG pipelines and optimizing retrieval-augmented generation workflows for production latency targets.
Distributed Systems at Scale: 15+ years architecting fault-tolerant, low-latency distributed systems. Expert-level understanding of consensus protocols, distributed state management, and data consistency models under partition. Experience with high-performance filesystems and storage engines optimized for AI workloads (checkpoints, model artifacts, training datasets).
AI Infrastructure & Platform Engineering: Built enterprise-grade or SaaS platforms specifically designed for AI/ML workloads—model registries, feature stores, inference gateways, and multi-tenant serving infrastructure. Deep familiarity with GPU/TPU cluster orchestration, memory hierarchy optimization, and heterogeneous compute scheduling.
High-Performance Data Planes: Designed and implemented high-throughput, low-latency networking stacks for critical data path operations. Expertise in RDMA, DPDK, kernel bypass techniques, and custom protocols for inter-service and accelerator-to-accelerator communication.
Security & Multi-Tenancy: Hardened multi-tenant ML infrastructure with robust isolation, end-to-end encryption, key management for model weights, and fine-grained RBAC/ABAC for data scientists and production workloads.
Cloud-Native Orchestration: Expert in Kubernetes scheduling extensions (device plugins, custom controllers), service mesh for AI microservices, and API gateway patterns for model serving.

Education