Description

You will architect and operate the core AI platform infrastructure for mission-critical applications.

This role is hybrid.

Responsibilities

• Deploy, manage, and troubleshoot containerized services on Kubernetes and OpenShift.
• Manage MLOps/LLMOps pipelines, deploying inference services using TensorRT-LLM and Triton Inference Server.
• Set up and operate AI inference service monitoring for performance and availability.
• Handle monitoring and load balancing for LLM models on the containerized platform.
• Operate mission-critical systems using standard incident and change management processes.

Required Skills

• 5+ years of experience in relevant engineering roles.
• Expertise with LLM deployment, configuration, and tuning using TensorRT-LLM.
• Deep experience with Kubernetes and OpenShift for container orchestration.
• Proficiency with Triton Inference Server architecture, configuration, and deployment.
• Experience implementing model optimization techniques (pruning, quantization, knowledge distillation).
• Ability to deploy models using containerization, microservices, and API design.
• Experience managing scalable infrastructure for LLM deployment.
• Familiarity with standard operational processes for mission-critical systems.

Preferred Skills

• Any Graduate.

Key Skills

Education

Any Graduate