AI Infrastructure Operations Engineer

About the role

Accenture’s Global AI Infrastructure team builds and operates large-scale GPU and accelerated-computing environments that power AI training, inference, simulation, and high-performance compute workloads across cloud, on-premises, and hybrid deployments. We design resilient, high-performance compute solutions, automate repeatable infrastructure tasks, and collaborate across the technology ecosystem to drive business transformation and deliver dependable services at scale.

Responsibilities

• Design and implement accelerated-computing infrastructure aligned to architecture, deployment roadmaps, performance, scalability, resiliency, and governance requirements.
• Deploy, configure, and operate GPU-based clusters across bare-metal and containerized environments using workload schedulers and Kubernetes orchestration for AI training, inference, and HPC workloads.
• Integrate infrastructure platforms with enterprise systems, data platforms, security frameworks, service-management processes, and governance controls.
• Design, build, and maintain reusable tools, scripts, self-service capabilities, and automation workflows for provisioning, configuration management, validation, capacity planning, monitoring, incident management, reporting, and remediation.
• Establish repeatable operational processes for cluster provisioning, configuration management, patching, capacity planning, monitoring, incident response, and lifecycle management.
• Perform and automate GPU, compute, storage, and network benchmarking and validation; diagnose performance issues across multi-node AI training, inference, and distributed compute workloads.
• Develop and maintain architecture diagrams, configuration baselines, operational runbooks, and support documentation.
• Provide technical guidance, troubleshooting, and optimization for GPU clusters supporting AI training, inference, HPC, and multi-node simulation workloads, emphasizing availability, resiliency, scalability, energy efficiency, and cost management.
• Travel may be required (25%–60% depending on business need and client requirements).

Requirements

• Minimum of 5+ years designing, deploying, and managing accelerated-computing infrastructure across on-premises, cloud, and hybrid environments for hyperscaler, neocloud, large enterprise, telecommunications, financial services, manufacturing, and/or retail clients.
• Minimum of 5+ years hands-on experience with accelerated-computing platforms, including GPUs, DPUs, and CPUs; high-bandwidth network fabrics; and AI-based storage architectures such as parallel file systems and NVMe-oF.
• Minimum of 5+ years experience with cluster management, workload scheduling, orchestration, observability, and infrastructure automation, including building operational tools and automation workflows with platforms such as Kubernetes and Slurm.
• Minimum 6 months hands-on experience with Claude Code, AI automation tools, Terraform, Ansible, Python, and Bash scripting.
• Bachelor’s degree or equivalent (minimum 12 years) work experience. (If Associate’s Degree, must have minimum 6 years work experience.)

Preferred Qualifications

• Experience building AI infrastructure automation and operations tools and adopting AgenticOps practices for secure, automated, governed, and reproducible platform operations.
• Experience developing reusable infrastructure code leveraging Python, platform services, and automation workflows using REST APIs, OpenAPI, JSON/YAML schemas, webhooks, and event-driven integrations.
• Experience operating large-scale GPU clusters, including capacity management, reliability engineering, change management, and performance validation for AI training, inference, HPC, and enterprise compute workloads.
• Experience using NVIDIA platform tools and libraries including Base Command Manager (BCM), NGC, NCCL, CUDA-X, NVAIE, Dynamo, and benchmarking tools to deploy, tune, profile, and validate cluster performance for training and inference workloads.
• Experience managing deployments of 1,000+ GPU clusters with infrastructure services enabled for AI training, inference, HPC, and enterprise compute environments.
• Design and build experience running LLMs across AI Cloud platforms from CoreWeave, Nebius, and other specialty providers.
• Knowledge of model deployments, tuning, and troubleshooting performance on AI Infrastructure.
• Industry certifications in accelerated-computing infrastructure, public cloud providers, infrastructure automation, networking, or security are a plus.

Pay

Compensation varies by office location, role, skill set, and experience. Below are annual salary ranges for select locations:

• California: $94,400 – $266,300
• Cleveland: $87,400 – $213,000
• Colorado: $94,400 – $230,000
• District of Columbia: $100,500 – $245,000
• Illinois: $87,400 – $230,000
• Maine: $80,400 – $196,000
• Maryland: $94,400 – $230,000
• Massachusetts: $94,400 – $245,000
• Minnesota: $94,400 – $230,000
• New York: $87,400 – $266,300
• New Jersey: $100,500 – $266,300
• Virginia: $87,400 – $245,000
• Washington: $100,500 – $245,000

Benefits

• Medical, dental, vision, life, and long-term disability coverage
• 401(k) plan with bonus opportunities
• Paid holidays and paid time off