Pallavi Sinha

With experience across Data Engineering and AI, I enjoy building innovative solutions to complex engineering challenges. My work has involved designing and implementing data platforms, developing AI-powered capabilities and exploring emerging technologies through research and experimentation.

Driven by curiosity and a passion for continuous learning, I enjoy combining analytical thinking with hands-on engineering to explore new ideas and build practical, scalable solutions. I share my learnings through technical writing and open-source contributions. I have also spoken at technology conferences, including XConf, sharing insights from my work and experience.

• Artificial intelligence: Large language models (LLMs), retrieval-augmented generation (RAG), AI agents, multi-agent systems, context engineering, knowledge graphs, and model evaluation and benchmarking.
  

• Data engineering: Distributed data processing, ETL/ELT pipeline, incremental processing, dimensional data modeling and data transformation.
  

• Data architecture: Medallion Lakehouse architecture, data mesh principles, domain-driven data products.
  

• Cloud: Microsoft Azure and AWS.
  

• Data governance and quality: Data governance, data lineage, data quality validation and data observability.
  

• Programming and databases: Python, SQL, PySpark, relational databases and graph databases.