Senior LLMOps Platform Engineer (GPU/Kubernetes)

Robotic Technologies Automation; Jersey City (NJ); On-site; USD 140,000 - 200,000; Full time

Job summary

ROBOTIC PROCESS AUTOMATION LLC seeks an AI Operations Platform Consultant to design, deploy, and operate GPU-accelerated LLM inference systems. You will manage containerized services on Kubernetes/OpenShift, implement robust deployment workflows, and ensure production reliability for mission-critical AI workloads.

You will lead monitoring, tracing, and performance tuning, applying mixed precision, quantization, and batching to optimize throughput and latency at scale in a Jersey City environment.

Qualifications

• Experience deploying containerized services at scale on Kubernetes/OpenShift.
• Experience with LLM inference pipelines and GPU-aware scheduling.

Responsibilities

• Deploy and manage containerized AI inference services in production.
• Maintain reliability and observability of LLM platforms across multi-node clusters.
• Optimize models and workloads using precision techniques and batching.

Skills

GPU-accelerated platforms

Kubernetes

Triton Inference Server

TensorRT-LLM

LLMOps / MLOps

CI/CD & deployment workflows

Tools

OpenShift

Job description

ROBOTIC PROCESS AUTOMATION LLC seeks an AI Operations Platform Consultant to design, deploy, and operate GPU-accelerated LLM inference systems. You will manage containerized services on Kubernetes/OpenShift, implement robust deployment workflows, and ensure production reliability for mission-critical AI workloads.

You will lead monitoring, tracing, and performance tuning, applying mixed precision, quantization, and batching to optimize throughput and latency at scale in a Jersey City environment.