• Design, develop, and maintain AI-powered applications using Python, Generative AI, and LLMs. • Develop and integrate LLM-based solutions for business applications and automation. • Build and maintain RAG pipelines to retrieve relevant information from enterprise data sources. • Implement prompt engineering techniques to improve AI response quality and accuracy. • Work with vector databases and vector stores for embeddings, semantic search, and information retrieval. • Develop and integrate AI gateways, MCP services, and guardrails for secure AI application development. • Integrate AI models using AWS Bedrock, Azure AI, or Google Cloud AI services. • Develop and maintain secure REST APIs using Python, AWS Lambda, and API Gateway. • Use AWS services such as S3, EC2, IAM, KMS, and container technologies to build and deploy applications. • Implement Infrastructure as Code using Terraform to automate cloud infrastructure provisioning. • Follow cloud-native development practices to build scalable, reliable, and secure applications. • Implement authentication, authorization, encryption, and access control mechanisms. • Develop and maintain CI/CD pipelines for automated application testing and deployment. • Work with Docker and container technologies for application deployment. • Monitor application performance, troubleshoot issues, and optimize cloud resource utilization. • Collaborate with developers, architects, DevOps teams, and business stakeholders to deliver technical solutions. • Participate in code reviews, technical discussions, and Agile/Scrum activities. • Maintain technical documentation and follow software development and cloud security best practices. Must-Have Skills • Python: Strong programming skills in Python for application development and automation. • Generative AI & LLMs: Experience developing applications using Generative AI and Large Language Models. • RAG: Knowledge of Retrieval-Augmented Generation, document processing, embeddings, and information retrieval. • Vector Databases: Experience with vector stores, semantic search, and similarity search. • AI Gateway, MCP & Guardrails: Understanding of AI gateways, Model Context Protocol, and AI security guardrails. • AWS Cloud Services: Hands-on experience with AWS Lambda, S3, API Gateway, EC2, IAM, KMS, and containers. • Cloud AI Platforms: Experience with AWS Bedrock, Azure AI, or Google Cloud AI. • Prompt Engineering: Ability to create and optimize prompts for LLM-based applications. • API Development: Experience developing and integrating RESTful APIs. • Terraform: Experience with Terraform for Infrastructure as Code and cloud resource management. • Cloud-Native Development: Understanding of scalable application architecture, cloud services, and distributed systems. • Cloud Security: Knowledge of authentication, authorization, encryption, and access management. • Software Engineering: Understanding of coding standards, testing, debugging, version control, and application development best practices. Good-to-Have Skills • Experience with CI/CD tools such as Jenkins, GitHub Actions, and GitLab CI. • Knowledge of Docker and container technologies. • Familiarity with AI productivity tools such as Cursor and GitHub Copilot. • Experience with Agile/Scrum methodologies and Jira. • Knowledge of cloud monitoring, logging, and deployment automation. • Experience with multi-region and multi-currency applications. • Understanding of security, governance, compliance, and data protection. • Good communication, problem-solving, and collaboration skills. • Ability to provide technical guidance and work effectively with cross-functional teams.