About the role
We are seeking a Cloud & AI Engineer with strong expertise in Artificial Intelligence, AWS, and Python to design, develop, and deploy scalable AI-powered applications. The ideal candidate will have hands-on experience with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architectures, AI Agents, serverless AWS services, and modern AI development frameworks. This role involves building enterprise-grade generative AI solutions, integrating cloud-native services, and implementing secure, production-ready AI systems.
Responsibilities
- Design, develop, and deploy AI-powered applications using AWS Cloud Services and modern AI frameworks.
- Build and optimize solutions leveraging Amazon Bedrock, Azure OpenAI, or other managed LLM platforms.
- Design and implement Retrieval-Augmented Generation (RAG) architectures, including embedding generation, vector databases, document chunking strategies, and retrieval workflows.
- Develop and manage AI Agents using Amazon Bedrock Agents, AgentCore, LangGraph, CrewAI, or similar agentic frameworks.
- Configure and integrate Model Context Protocol (MCP) servers and tools to enable secure communication between AI models and enterprise systems.
- Develop robust Python applications, including:
- AWS Lambda functions
- API integrations
- AI orchestration workflows
- Data processing pipelines
- Utilize frameworks such as LangChain, LlamaIndex, and AWS SDK (boto3) for AI solution development.
- Design and implement serverless architectures using:
- AWS Lambda
- API Gateway
- Amazon S3
- DynamoDB
- EventBridge
- Step Functions
- Develop effective prompts, prompt templates, and guardrails to ensure reliable and safe AI system behavior.
- Optimize application performance, scalability, security, and operational efficiency.
- Collaborate with business stakeholders, architects, and development teams to translate requirements into technical solutions.
- Support deployment, monitoring, troubleshooting, and continuous improvement of AI and cloud-based platforms.
- Document solution architecture, technical designs, implementation details, and operational procedures.
- Stay updated with emerging Generative AI technologies, AWS services, and industry best practices.
Requirements
- Strong experience in Generative AI, AWS Cloud, and Python Development.
- Hands-on expertise with Amazon Bedrock and/or Azure OpenAI.
- Proven experience building RAG (Retrieval-Augmented Generation) solutions, including vector databases, semantic search, and knowledge retrieval systems.
- Strong understanding of Prompt Engineering, AI Guardrails, AI Safety Controls, and Responsible AI practices.
- Experience with AI Agents using Bedrock Agents, AgentCore, LangGraph, CrewAI, or similar frameworks.
- Strong Python development skills with experience in AWS Lambda, boto3, LangChain, and LlamaIndex.
- Hands-on experience designing and implementing AWS serverless architectures using Lambda, API Gateway, S3, DynamoDB, EventBridge, and Step Functions.
- Familiarity with Model Context Protocol (MCP) and enterprise AI integrations.
- Excellent analytical, troubleshooting, communication, and stakeholder management skills.
Preferred Qualifications
Experience with Docker, Kubernetes, Amazon ECS/EKS, and modern DevOps practices including Git, CI/CD pipelines, Terraform, and CloudFormation. Exposure to MLOps, AI deployment pipelines, monitoring, and observability tools such as CloudWatch, Prometheus, and Grafana is preferred. AWS certifications and experience delivering enterprise-scale, production-grade Generative AI solutions will be a strong advantage