Note: The job is a remote job and is open to candidates in USA. Dice is seeking a Senior AI Engineer with strong experience in NVIDIA AI technologies, specifically NVIDIA NIM Microservices and Triton Inference Server. The ideal candidate will be responsible for designing, deploying, optimizing, and scaling Generative AI and LLM-based applications in enterprise environments.

Responsibilities

• Design and deploy AI applications using NVIDIA NIM Microservices
• Build and optimize model serving infrastructure using Triton Inference Server
• Deploy and manage LLM workloads in Kubernetes environments
• Optimize inference performance using TensorRT-LLM and CUDA
• Collaborate with Data Science, MLOps, and Platform Engineering teams
• Implement scalable, secure, and production-ready AI solutions
• Troubleshoot and improve AI application performance and reliability
• Support cloud-based AI deployments across AWS, Azure, or Google Cloud Platform

Skills

• Hands-on experience with NVIDIA NIM Microservices
• Strong experience with NVIDIA Triton Inference Server
• Experience deploying and serving Large Language Models (LLMs)
• Knowledge of TensorRT-LLM and CUDA optimization
• Experience with Kubernetes and Docker containerization
• Strong Python programming skills
• Experience building AI/ML applications in AWS, Azure, or Google Cloud Platform
• Understanding of model inference, model serving, and performance tuning
• Experience with REST APIs and microservices architecture
• Experience with NVIDIA NeMo
• Experience with RAG (Retrieval-Augmented Generation) architectures
• Familiarity with LangChain or LlamaIndex
• Exposure to MLOps/LLMOps practices
• Experience with monitoring and observability tools

Company Overview

Company H1B Sponsorship