Description

You will design and implement scalable AI/ML solutions on AWS, focusing on RAG architectures, AI agents, and enterprise platform integration.

This role is on-site.

Responsibilities

• Lead onboarding of business applications onto the enterprise AI platform, translating requirements into AWS infrastructure capabilities.
• Design and implement Retrieval-Augmented Generation (RAG) systems, AI agents, and multi-agent workflows using AWS Bedrock and SageMaker.
• Architect cloud-native AI solutions, ensuring high availability, security, and governance through IAM, VPC, and AI guardrails.
• Develop reusable AI integration patterns, orchestration components, and reference architectures for cross-team adoption.
• Coordinate with Cloud Infrastructure, Security, Data Engineering, and Application Development teams to drive technical delivery.

Required Skills

• 10+ years of experience in Cloud Engineering, Platform Engineering, or Enterprise Architecture.
• 4+ years designing and implementing AI/ML and Generative AI solutions.
• 2+ years hands-on experience building RAG systems and AI Agents.
• Deep expertise in AWS services: VPC, IAM, EC2, ECS, EKS, Lambda, S3, API Gateway, CloudFormation, Bedrock, SageMaker, and Step Functions.
• Proficiency in Python and Java, with experience in REST APIs and SDK integration.
• Strong understanding of RAG architecture, vector databases, embeddings, semantic search, and prompt engineering.
• Experience with AI governance, hallucination mitigation, and responsible AI controls.
• Hands-on with Terraform, CI/CD, Git, and data ingestion pipelines.

Preferred Skills

• Experience in large enterprise or financial services environments.
• Familiarity with LangChain, LangGraph, LlamaIndex, and multi-agent orchestration frameworks.

Key Skills

Education

Any Graduate