Job Type: Full Time

Job Category: IT

Job Description

Job Title :  AI AWS Architect

Location : Parsippany, NJ (ONSITE)
Full Time ONLY

Job Description

Must Have Technical/Functional Skills

·         10+ years of experience in Software Development & ML engineering, including 4+ years in Solution architecture or AI architecture delivering production-grade systems.

·         Strong hands-on expertise in Python (workflow orchestration, model evaluation), Node.js, and experience working with agent-based frameworks such as AutoGen, LangChain, or ADK. Solid knowledge of prompt engineering techniques and tool-calling mechanisms.

·         Deep understanding of retrieval-augmented systems, including embeddings, chunking strategies, ranking mechanisms, and Vector databases such as Qdrant and MongoDB Atlas with vector search capabilities.

·         Extensive experience in MLOps practices, including CI/CD pipelines for ML models, model registry management, and containerized deployments using Kubernetes.

·         Strong cloud expertise in AWS, with hands-on experience in services such as Amazon Bedrock, SageMaker, AWS Lambda, and Amazon EKS.

·         Demonstrated experience in implementing Responsible AI practices, security best practices (encryption, secrets management, network isolation), and FinOps strategies for AI workloads, including cost and latency optimization.

Roles & Responsibilities

·         Architect and design an end-to-end solution for an AI-driven Retrieval-Augmented system.

·         Define and implement the embedding strategy, document chunking methodology, and ranking techniques to ensure high-quality retrieval.

·         Evaluate, select, and integrate appropriate Large Language Models (LLMs) using Amazon Bedrock.

·         Design and implement a scalable vector database solution (such as OpenSearch, Qdrant, or MongoDB Atlas with vector search).

·         Architect and deploy the cloud infrastructure leveraging AWS services including Amazon Bedrock (LLM), SageMaker, AWS Lambda, and Amazon EKS.

·         Establish MLOps best practices by designing CI/CD pipelines for model deployment and managing model registry updates.

·         Apply FinOps principles to balance cost and performance, optimizing model size, inference latency, and caching strategies.

·         Design secure access controls and implement secrets management using AWS Secrets Manager.

Required Skills