Senior AI Infrastructure Lead: GPU Clusters & LLMs

Cadence Design Systems; San Jose (CA); On-site; USD 137,000 - 254,000; Full time

Job summary

Cadence Design Systems in San Jose seeks a Senior AI Systems Engineer to own the AI infrastructure lifecycle, from architecting GPU clusters to deploying advanced models.

The role combines hands-on GPU cluster management, LLM deployment, and production-grade agentic workflows, with emphasis on Docker, Kubernetes, PyTorch, TensorFlow, and CI/CD.

You will collaborate across on-prem and cloud (Azure OpenAI, GCP) and mentor engineers while ensuring security and performance.

Qualifications

• 10+ years in a senior technical role, with at least 5 years focused on building and operating high-performance computing or AI infrastructure.
• Expert-level knowledge of NVIDIA GPU architecture and technologies like CUDA and cuDNN.
• Proven experience with public cloud AI services, specifically Azure OpenAI and Google Cloud Platform (GCP).
• Extensive hands-on experience with Docker: image management, container orchestration, and troubleshooting.

Responsibilities

• AI Infrastructure Architecture & Strategy: Lead the design and implementation of next-gen AI infrastructure for Agentic AI initiatives.
• Cloud AI Service Integration: Manage access, usage, and billing for Azure OpenAI and GCP services.
• Hands-on GPU Cluster Management: Configure, install, and optimize GPU server clusters, troubleshoot hardware/software, tune performance.
• Full-Stack AI Tech Stack Development & Operations: Deploy and maintain PyTorch, TensorFlow, Docker, Kubernetes, and CI/CD pipelines.
• Advanced LLM Deployment & Optimization: Deploy and optimize LLMs using vLLM, TGI, TensorRT-LLM for high throughput and low latency.
• Agentic AI Workflow & Service Engineering: Build production-grade AI workflows integrating LLMs with tools, APIs, and databases; mentor engineers.
• Automation & Monitoring: Create automation scripts (Python/Bash/Perl); monitor system health, GPU utilization, container performance.
• AI Systems Support & Mentorship: Provide escalation engineering support and technical leadership on AI systems engineering and performance tuning.
• Security and Compliance: Implement security best practices for AI systems and data.

Skills

NVIDIA GPU architecture

CUDA

cuDNN

Azure OpenAI

GCP

Docker

Kubernetes

Python

Bash

Linux system administration

Tools

LSF

Docker

Kubernetes

CI/CD

Job description

Cadence Design Systems in San Jose seeks a Senior AI Systems Engineer to own the AI infrastructure lifecycle, from architecting GPU clusters to deploying advanced models.

The role combines hands-on GPU cluster management, LLM deployment, and production-grade agentic workflows, with emphasis on Docker, Kubernetes, PyTorch, TensorFlow, and CI/CD.

You will collaborate across on-prem and cloud (Azure OpenAI, GCP) and mentor engineers while ensuring security and performance.