Distinguished Engineer - AI

About the role

NetApp is looking for a Distinguished Engineer with deep expertise in AI/ML inferencing at scale and the distributed systems foundations behind it. The role sits within the ONTAP team, which defines the product strategy, roadmap and engineering delivery for ONTAP software and systems. You will architect and ship the next-generation AI infrastructure and inferencing platform serving millions of requests with strict latency, throughput and reliability requirements.

Key responsibilities

• Set the technology strategy and define the roadmap and long-term vision from business priorities, technology and competitive trends.
• Partner with Product management and engineering to define and deliver next-generation products.
• Influence executive management and engineering, acting as a force multiplier across engineers.
• Mentor senior and principal engineers and raise the technical bar for those roles.
• Evaluate internally and externally for NetApp products and become an industry authority on related technologies.

Required profile

• Recognized domain expert in software and system design for highly scalable distributed storage and databases, including control and data plane architectures for Gen AI and AI-as-a-Service workloads.
• 15+ years architecting fault-tolerant, low-latency distributed systems, with expert knowledge of consensus protocols, distributed state management and data consistency under partition.
• Experience building resilient, scalable enterprise products and large-scale, compute-intensive stateful applications.
• Proven track record building, architecting RAG pipelines and optimizing retrieval-augmented generation workflows for production latency targets.
• Excellent communication skills with executives and senior leadership.

Required skills

• High-performance inference engines (TensorRT, vLLM, ONNX Runtime, Triton), model optimization (quantization, pruning, distillation) and serving patterns for LLMs and computer vision models.
• Enterprise-grade or SaaS AI/ML platforms: model registries, feature stores, inference gateways, multi-tenant serving infrastructure; GPU/TPU cluster orchestration.
• High-throughput, low-latency networking stacks, RDMA, DPDK, kernel bypass and custom protocols.
• Multi-tenant isolation, encryption, key management and RBAC/ABAC.
• Kubernetes scheduling extensions, service mesh and API gateway patterns for model serving.

What we offer

• Target OTE of 266,050 - 396,000 USD, depending on location, qualifications and experience.
• Benefits such as health insurance, life insurance, retirement plans, paid time off, employee stock purchase plan and/or RSUs.
• A hybrid working environment, with in-office expectations shared during recruitment.

Applications are submitted only through the company website; direct contact with employees or recruiters does not affect the process.