Job Title

You can share resumes to The position is based out in Mumbai. Position: Full Stack AI Cloud Engineer (Python, ReactJs, AWS, Vector DB & LLM) Qualifications: Bachelor’s or master’s degree in computer science or related field. 7+ years of experience in Software Engineering/Development 3+ years of experience in Python 3+ years of experience in ReactJs 2+ years of experience in AWS, SAM, services - Lambda, Glue, Cognito, Bedrock, AppSync & Amplify 1+ years of experience in Vector DB & LLM Requirements: Backend (Python): Strong experience in Python with Flask / FastAPI frameworks. Experience in Microservices developments using AWS Lambda Experience in data processing pipelines using PySpark in AWS Glue Strong knowledge of relational databases like PostgreSQL or MySQL. Experience with NumPy and Pandas for data processing. Knowledge of Celery, Redis/RabbitMQ/ AWS SQS message queues for asynchronous task processing. Frontend (React.js): Strong hands-on experience in React.js, including Redux, Hooks, Context API. Proficiency in JavaScript (ES6+) and TypeScript. Proficiency in writing reusable and scalable React components. Strong knowledge of JavaScript (ES6+), TypeScript, HTML5, CSS3, and responsive UI design. Experience with frontend testing frameworks like Jest, React Testing Library. General & DevOps Skills: Experience with CI/CD pipelines Good understanding of Git workflows and version control. Knowledge of API documentation tools like Swagger/OpenAPI. Familiarity with Agile methodologies like Scrum/Kanban & Jira project management tool. Roles & Responsibilities: Backend Development: Design, develop, and maintain RESTful APIs using Flask or FastAPI. Develop microservices using AWS Lambda functions and ETL jobs using AWS Glue & PySpark Cleanse, transform, and analyze complex datasets to support business insights and analytics using PySpark. Optimize PySpark jobs for performance and scalability. Work with Pandas & NumPy for data transformation and analytics. Frontend Development: Build modern, scalable, and maintainable React.js applications. Develop responsive UI components and integrate with backend APIs. Implement state management using Redux/Context API. Write clean, efficient, and reusable code following best practices. Optimize performance, accessibility, and frontend security. AWS: Serverless Application Development (AWS SAM & Lambda) Design and deploy serverless applications using AWS SAM (Serverless Application Model) to automate infrastructure provisioning. Develop, test, and maintain AWS Lambda functions for real-time data processing, microservices, and backend automation. Data Engineering with AWS Glue Create ETL pipelines with AWS Glue to transform, clean, and catalog structured and semi-structured data. Develop Glue Jobs using PySpark and monitor performance, scaling, and job triggers. Integrate Glue with data lakes and other AWS data sources S3, and Aurora. Authentication and Access Control (AWS Cognito) Implement secure user authentication and authorization using AWS Cognito (user pools and identity pools). Customize token policies, integrate social logins (OAuth2, SAML), and manage identity federation. AWS Bedrock & LLMs Utilize AWS Bedrock to build, test, and fine-tune LLM-powered applications using models like Anthropic Claude, Meta Llama, or Amazon Titan. Design prompt engineering strategies, fine-tuning workflows, and RAG (Retrieval-Augmented Generation) architectures. GraphQL API Design (AWS AppSync) Design scalable GraphQL APIs with AWS AppSync to simplify front-end/backend integration. Implement resolvers using Lambda, DynamoDB, and Aurora Serverless data sources. Handle schema stitching, caching, real-time subscriptions, and access control. Frontend Integration & DevOps (AWS Amplify) Integrate front-end apps (React) with Amplify for CI/CD, hosting, and backend service integration. Configure Amplify with GraphQL endpoints (AppSync), Cognito auth, and storage modules. Manage deployment pipelines and environment-specific builds. Vector Store Design & Search Design schema for storing dense vector embeddings from LLMs or NLP pipelines. Integrate vector DBs with LLMs using frameworks like LangChain, or custom RAG workflows. Deployment & Performance Optimization: Optimize APIs and database queries for high performance. Deploy and manage applications using Docker, Kubernetes (EKS / ECS). Implement unit tests, integration tests, and maintain code quality.