• Rajesh Sura

Major advances in data engineering result from the adoption of generative artificial intelligence, especially through large language models (LLMs). Generative AI technologies improve productivity by handling manual SQL generation and developing ETL pipelines, and creating documentation, which also minimizes human errors and broadens complex data workflow access to non-experts. This review investigates modern generative AI technologies in data engineering through the evaluation of essential tools, together with theoretical constructs and experimental findings, and architectural integration strategies. It discusses the enhancements alongside the boundaries of implementing LLMs to automate essential data procedures. Examining research outcomes along with experimental results enables the study to present use case examples and performance parameters while defining optimal practices. It concludes by introducing directions for future investigations with guidelines for better generative AI implementation in production-level data engineering systems.

Generative AI, Data Engineering, SQL Generation, ETL Automation, LLMs, Prompt Engineering, Data Pipeline Documentation, NLP for Code, Machine Learning, GPT-4.

"GENERATIVE AI FOR DATA ENGINEERING: AUTOMATING SQL GENERATION, ETL DESIGN, AND PIPELINE DOCUMENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.b302-b309, May-2025, Available :http://www.jetir.org/papers/JETIR2505136.pdf

"GENERATIVE AI FOR DATA ENGINEERING: AUTOMATING SQL GENERATION, ETL DESIGN, AND PIPELINE DOCUMENTATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppb302-b309, May-2025, Available at : http://www.jetir.org/papers/JETIR2505136.pdf