Description

Key Skills: Python, SQL, AWS, Databricks, Delta Lake, ETL/ELT, Data Engineering, PySpark, PostgreSQL, RESTful APIs

Good to Have Skills: LLM APIs integration (OpenAI, AWS Bedrock, Anthropic Claude), Vector databases (pgvector, Pinecone, OpenSearch), RAG pipelines, LangChain, LlamaIndex, FastAPI, Flask, Django, OAuth 2.0, JWT, RBAC, OWASP guidelines, Cloudera Data Platform (CDP), MySQL, Prompt engineering, API security standards, Agile methodology experience, Enterprise functions domain knowledge (HR/Finance/Compliance/Procurement).

Roles & Responsibilities:

• Enhance and deliver high quality data products and analytic ready data solutions for enabling functions.
• Work with stakeholders to define overall strategy for organization's data products and new features.
• Develop and implement data engineering solutions that support the organization's business needs using various technologies.
• Understand and collaborate with data architect to maintain data models to support reporting and analysis needs.
• Optimize data storage and retrieval to ensure efficient performance and scalability of data systems.
• Implement standard data governance policies and procedures to ensure data accuracy, consistency, and security.
• Partner closely with Enterprise Data and Analytics Platform team and other functional data pods.
• Stay up to date with industry trends in data architecture, data engineering and technology advancements.
• Design and develop RESTful APIs to expose data products and analytics capabilities to business applications.
• Build reusable API frameworks to accelerate development across multiple enterprise use cases and workflows.
• Integrate LLM APIs into enterprise workflows for natural language querying, document summarization, and conversational AI.
• Build RAG pipelines using vector databases combined with LLM APIs for enhanced data retrieval.
• Leverage orchestration frameworks to build multi-step AI agents and automated workflows for business processes.
• Build ETL/ELT pipelines and work with lakehouse concepts including medallion architecture and bronze/silver/gold layers.

Experience Required: 3-5 years of experience in information technology field developing AWS cloud native data lakes and ecosystems with production support experience. At least 1-2 years of experience in onshore offshore delivery model

Key Skills

Education

Any Graduate