AI Full Stack Engineer – Integration & GenAI

AI Full Stack Engineer – Integration & GenAI

Responsibilities

1. Analyze business and technical requirements and translate them into end-to-end system, data flow, and integration designs.
2. Design and develop REST APIs, SFTP, file-based interfaces, and batch integrations across upstream and downstream enterprise systems.
3. Develop Python scripts and backend services for data extraction, transformation, validation, automation, and system integration.
4. Design and implement reliable data pipelines and data movement across enterprise platforms, Data Lake, and downstream applications.
5. Perform data mapping, transformation, aggregation, reconciliation, and data quality validation to ensure accurate data delivery.
6. Support GenAI and RAG use cases through document ingestion, data preparation, enrichment, transformation, and AI-ready data pipelines.
7. Develop and maintain application components using Python, SQL, Celery, HTML, Jinja, and TypeScript.
8. Support SIT, UAT, deployment, production troubleshooting, incident resolution, and application enhancements.
9. Work with Docker, Kubernetes/OpenShift, CI/CD, Git, Jenkins, Control-M, and monitoring tools to ensure reliable application delivery.
10. Collaborate with business, application, data, infrastructure, security, and architecture teams to resolve issues and deliver scalable solutions.

Requirements

1. Minimum of 3 years relevant experience in System Analysis, Integration Engineering, Data Engineering, Full Stack Engineering, or Technical Delivery roles.
2. Strong hands-on experience in Python and SQL for development, data handling, automation, integration, and troubleshooting.
3. Practical experience developing and integrating REST APIs, SFTP, batch processes, and file-based interfaces.
4. Strong understanding of data mapping, transformation, aggregation, reconciliation, data quality, and enterprise data flows.
5. Experience with enterprise data platforms such as Informatica, Cloudera, Data Lake, or similar technologies.
6. Good knowledge of Celery, Docker, Kubernetes/OpenShift, CI/CD, Git, Jenkins, and Bash.
7. Working knowledge of HTML, Jinja, and TypeScript with exposure to application/UI development.
8. Experience supporting SIT/UAT, production deployments, incident management, debugging, and application enhancements.
9. Exposure to GenAI concepts including document ingestion, RAG, embeddings, data preparation, and AI-enabled workflows; ML model development is not mandatory.
10. Strong stakeholder management skills, with the ability to understand complex enterprise ecosystems.

Skills

Retrieval-Augmented Generation (RAG), Model Driven Development, Python Scripting, REST APIs development, Data Quality Assurance, Business Requirement Analysis, Enterprise Systems, Data Lake, Production Deployment, CI/CD, Sit Testing, Develop Software Components, Rest Apis, Scripting Languages, Data Infrastructure, SQL Development