AI Engineer

AgreeYa Solutions, Inc.

United States

about 2 months ago

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Expert

Working hours

Regular working hours

Job source

dice.com

Tech stack

Artificial Intelligence Amazon Web Services Microsoft Azure Nvidia CUDA Monitoring of Systems Python (Programming Language) Machine Learning Performance Tuning Google Cloud Retrieval-Augmented Generation Large Language Models Generative AI

+8 more

Containerization Kubernetes Machine Learning Operations TensorRT Nim (Programming Language) Restful APIs Docker Microservices

Job description

We are 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., * 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

Requirements

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

Preferred Skills

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

About the company

AgreeYa is a global systems integrator delivering a competitive advantage for its customers through software, solutions, and services. Established in 1999, AgreeYa is headquartered in Folsom, California, with a global footprint and a team of more than 1,800+ professionals across offices. AgreeYa works with 550+ organizations ranging from Fortune 100 firms to small and large businesses across industries such as Telecom, Banking, Financial Services & Insurance, Healthcare, Utility & Energy, Technology, Public Sector, Pharma & Biotech, Retail, Client, and others. Please visit us at for more information.