Description

Design and build generative AI-powered applications on AWS using Python and AWS Bedrock.

This role is on-site.

Responsibilities

• Develop and deploy AI applications using AWS Bedrock, integrating models like Anthropic Claude and Amazon Titan.
• Build backend services using Python (FastAPI, Flask) and create APIs to integrate AI models into applications.
• Design and optimize prompt engineering strategies and build use cases such as chatbots, document summarization, and Q&A systems.
• Develop Retrieval-Augmented Generation (RAG) pipelines, handling preprocessing, embedding, and inference workflows with vector databases.
• Implement secure, scalable cloud-native architectures using AWS Lambda, API Gateway, S3, DynamoDB, and IAM policies.

Required Skills

• 6+ years of experience in Python development.
• Hands-on experience with AWS services including Lambda, API Gateway, S3, DynamoDB, IAM, and VPC.
• Strong proficiency in Python REST API development using FastAPI or Flask.
• Experience with AWS Bedrock or Generative AI programming.
• Knowledge of serverless architecture and LLM-based applications.
• Familiarity with prompt engineering and RAG concepts.
• Experience implementing CI/CD pipelines using GitHub Actions.

Preferred Skills

• Experience with LangChain, LlamaIndex, or Terraform (IaC).
• Knowledge of vector databases such as FAISS, Pinecone, or OpenSearch.
• AWS Certifications (Solutions Architect or AI Specialty).

Key Skills

Education

Any Gradute