Job Description

ELEVI is seeking an AI Operations Platform Consultant to deploy, manage, and troubleshoot containerized services on Kubernetes, focusing on LLMs using TensorRT-LLM and Triton Inference Server. The role involves managing MLOps/LLMOps pipelines, monitoring AI inference services, and ensuring the operational stability of mission-critical systems.

Responsibilities

• Deploying and managing containerized services on Kubernetes
• Deploying, configuring, and tuning LLMs using TensorRT-LLM and Triton Inference server
• Managing MLOps/LLMOps pipelines
• Setting up and operating AI inference service monitoring
• Deploying and troubleshooting LLM models
• Managing scalable infrastructure for LLMs
• Deploying models in production environments
• Operating mission critical systems - incident, change, and event management

Requirements

• Experience with Kubernetes and OpenShift
• Experience with TensorRT-LLM and Triton Inference server
• Experience deploying and troubleshooting LLM models
• Experience with containerization, microservices, and API design
• Knowledge of model optimization techniques

Benefits

• No benefits