Description

You will design, develop, and deploy scalable Generative AI applications on AWS, owning the full lifecycle from data pipelines to production workloads.

This role is on-site.

Responsibilities

• Build and optimize serverless applications using AWS Lambda and API Gateway to expose AI capabilities.
• Design and implement Retrieval-Augmented Generation (RAG) architectures using Amazon Bedrock and vector databases like OpenSearch.
• Develop intelligent AI agents and agentic workflows for enterprise automation, ensuring secure access via IAM.
• Deploy and manage AI workloads on Amazon ECS/EKS while monitoring performance with CloudWatch.
• Fine-tune foundation models, perform prompt engineering, and ensure Responsible AI governance and compliance.

Required Skills

• 5+ years of experience designing and deploying Generative AI applications.
• Deep expertise with Amazon Bedrock, LLMs, and foundation model fine-tuning.
• Strong proficiency in AWS serverless services: Lambda, API Gateway, S3, DynamoDB, and OpenSearch.
• Experience building RAG architectures and vector search implementations.
• Hands-on experience with container orchestration using Amazon ECS or EKS.
• Proven ability to design secure, scalable AI data pipelines.
• Ability to communicate technical AI concepts to business stakeholders.

Preferred Skills

• Experience with Agentic workflows and enterprise automation patterns.
• Background in prompt engineering optimization for multiple use cases.

Key Skills

Education

Any Graduate