Senior LLMOps Platform Engineer on Kubernetes

Valiant Technologies LLC; Jersey City (NJ); On-site; USD 120,000 - 190,000; Full time

Job summary

VALIANT TECHNOLOGIES LLC is seeking an AI Operations Platform Consultant to deploy and manage GPU-accelerated AI platforms on Kubernetes, focusing on LLM inference with Triton Inference Server and TensorRT-LLM. You will build production pipelines, implement robust deployment workflows, and ensure observability with telemetry and dashboards for latency, throughput and reliability in multi-node clusters.

The role requires experience operating containerized services at scale (OpenShift), strong

Qualifications

• Experience operating large-scale GPU-accelerated AI platforms.
• Experience deploying LLM inference systems on Kubernetes.
• Experience with MLOps/LLMOps pipelines and deploying inference services in production.
• Set up and operate AI inference service monitoring for performance and availability.

Responsibilities

• Operate GPU-accelerated AI platforms on Kubernetes for production workloads.
• Deploy and manage LLM inference services using Triton and TensorRT-LLM.
• Establish observability with telemetry and dashboards to monitor latency, throughput and availability.
• Lead end-to-end deployment workflows and ensure reliability in multi-node clusters.

Skills

GPU platforms

Kubernetes

Triton Inference

TensorRT-LLM

MLOps/LLMOps

Observability

Containerized microservices

OpenShift

Load balancing

Tools

Triton Inference Server

TensorRT-LLM

OpenShift

Job description

VALIANT TECHNOLOGIES LLC is seeking an AI Operations Platform Consultant to deploy and manage GPU-accelerated AI platforms on Kubernetes, focusing on LLM inference with Triton Inference Server and TensorRT-LLM. You will build production pipelines, implement robust deployment workflows, and ensure observability with telemetry and dashboards for latency, throughput and reliability in multi-node clusters.

The role requires experience operating containerized services at scale (OpenShift), strong