Senior LLMOps Platform Engineer — GPU AI Infra

Quantum Technologies. LLC; Jersey City, Northern (NJ, KY); Hybrid; USD 120,000 - 165,000; Full time

Job summary

QUANTUM TECHNOLOGIES LLC in the United States seeks an AI Operations Platform Consultant to deploy, operate, and troubleshoot containerized AI services at scale on Kubernetes (OpenShift). You will configure LLM inference pipelines using TensorRT-LLM and Triton Inference Server, implement robust deployment workflows, and build observability for GPU health and performance.

This role requires enterprise experience with MLOps/LLMOps, incident management, and scalable infrastructure, ensuring

Qualifications

• Experience deploying and operating containerized AI services at scale.
• Hands-on with TensorRT-LLM and Triton Inference Server in production.
• Strong knowledge of MLOps/LLMOps pipelines and model versioning.
• Experience with monitoring GPU health, latency, and throughput.
• Security-conscious runtime controls and reliability focus.

Responsibilities

• Deploy and manage production-grade LLM inference services on Kubernetes (OpenShift).
• Tune and optimize models with mixed precision, quantization, and batching.
• Design and implement observability dashboards and alerts for inference systems.
• Ensure reliability, incident management, and scalable infrastructure.

Skills

GPU-accelerated AI platforms

Kubernetes

LLM inference

MLOps/LLMOps

Observability and telemetry

Containerized microservices

Tools

TensorRT-LLM

Triton Inference Server

OpenShift

Container orchestration

Job description

QUANTUM TECHNOLOGIES LLC in the United States seeks an AI Operations Platform Consultant to deploy, operate, and troubleshoot containerized AI services at scale on Kubernetes (OpenShift). You will configure LLM inference pipelines using TensorRT-LLM and Triton Inference Server, implement robust deployment workflows, and build observability for GPU health and performance.

This role requires enterprise experience with MLOps/LLMOps, incident management, and scalable infrastructure, ensuring