AI Ops Engineer

Position:

Location:

Duration:

About the Role

AI Ops Engineer

designing, implementing, and optimizing AI infrastructure

hands-on and customer-facing role

Responsibilities

• Deploy and operationalize NVIDIA AI and open-source AI application blueprints.
• Design and optimize

  AI/ML infrastructure

  leveraging Kubernetes and GPU acceleration.
• Implement and manage

  model inferencing pipelines

  using Triton Inference Server, NeMo, and NIM.
• Collaborate with enterprise IT and data science teams to integrate AI workloads into production.
• Automate deployments and monitoring with

  Python, Bash, and DevOps tools

  .
• Troubleshoot infrastructure and model performance issues in customer environments.
• Act as a

  trusted advisor

  to enterprise customers, ensuring successful AI solution delivery.

Required Qualifications

• Proven expertise in

  Kubernetes

  and containerized application deployment.
• Hands-on experience with

  AI/ML model inferencing pipelines

  .
• Strong knowledge of

  NVIDIA AI technologies

  (NeMo, NIM, Triton Inference Server, CUDA).
• Experience deploying

  AI blueprints/reference architectures

  from NVIDIA or open-source communities.
• Strong

  scripting and automation

  skills (Python, Bash).
• Excellent

  communication and consulting

  experience with enterprise customers.

Preferred Qualifications

• Familiarity with

  MLOps tools and CI/CD pipelines

  .
• Experience working with

  enterprise IT and data science teams

  .
• Background in

  AI performance tuning

  and

  scalable infrastructure design

  .