Full Stack AI and Data Engineer - AWS

Accountabilities:: Design and develop scalable data pipelines that ingest information from REST APIs, databases, files, and other enterprise data sources, using Python, PySpark, AWS Glue, and appropriate AWS services for transformation and processing. Build and orchestrate data workflows using AWS Step Functions and establish S3-based data layers for raw, processed, and curated datasets, while maintaining Athena and Glue Catalog layers for efficient querying and downstream consumption. Design and develop Python-based backend services and REST APIs, creating modular microservices that can support AI agents, front-end applications, enterprise integrations, and third-party systems. Implement robust backend capabilities including authentication, input validation, error handling, logging, monitoring, and reliable deployment using suitable AWS or cloud technologies. Design and build AI agents using Amazon Bedrock, AgentCore, Strands, and related technologies, enabling agents to interact with enterprise data, APIs, backend services, and business applications. Implement agent tools and function calling, workflows, context management, and Retrieval-Augmented Generation where appropriate, while integrating LLMs with enterprise applications and data sources. Apply effective practices for prompt management, AI evaluation, security, observability, and cost optimization, while developing reusable agent frameworks and components that can support multiple enterprise AI use cases. Develop clean, modular, reusable, and testable code while following Git, code review, CI/CD, configuration-driven development, security, secrets management, logging, monitoring, and access-control standards. Contribute to Infrastructure as Code and cloud deployment practices, with Terraform experience particularly valued for provisioning and managing AWS infrastructure. Requirements: 5+ years of overall software or data engineering experience, with meaningful hands-on expertise across AWS, Python, modern data engineering, and AI or GenAI technologies. Strong hands-on Python development skills and substantial AWS development experience, combined with practical experience building data pipelines and ETL processes. Experience with PySpark and preferably AWS Glue, along with strong knowledge of S3 and Athena or equivalent cloud data-lake technologies. Experience with workflow orchestration technologies such as AWS Step Functions and the ability to design reliable, scalable data-processing architectures. Proven experience developing REST APIs and backend services, including integrations with enterprise systems and third-party APIs. Hands-on experience developing LLM/GenAI applications or AI agents, with practical experience using Amazon Bedrock; exposure to AgentCore and/or Strands is highly desirable. Strong understanding of software engineering practices, Git, CI/CD, clean-code principles, testing, deployment, security, and production operations. Experience with Terraform or Infrastructure as Code, Docker and containerized deployments, RAG, vector databases, embeddings, AI evaluation, and observability is advantageous. Familiarity with AWS Lambda, API Gateway, EventBridge, DynamoDB, React/Next.js, or front-end integration is a plus, as is experience integrating platforms such as Salesforce, SAP, or ServiceNow. Knowledge of LangChain, LangGraph, or similar agent frameworks is beneficial, particularly for building enterprise-grade agentic AI solutions. Strong candidates will demonstrate breadth across AWS, Python, Data Engineering, and GenAI/Agentic AI rather than deep expertise limited to only one technical area. Ability to work independently, collaborate effectively across technical domains, and operate comfortably in a hands-on, fast-moving engineering environment. Benefits: Six-month contract opportunity focused on modern AI, data engineering, backend development, and AWS cloud technologies. Fully remote position for candidates based in India. Opportunity to work across the full solution lifecycle, from architecture and development through deployment and productionization. Hands-on exposure to AWS services including Glue, Step Functions, S3, Athena, Bedrock, and related cloud technologies. Opportunity to build enterprise AI agents and reusable GenAI capabilities using modern agentic AI frameworks. Cross-functional technical scope spanning Data Engineering, AI/LLM applications, backend APIs, microservices, DevOps, and cloud infrastructure. Opportunity to work with modern engineering practices including CI/CD, Infrastructure as Code, containerization, observability, and secure cloud deployment.