🚀 Cloud Data & AI Engineer | Azure | AWS | GCP

I’m a Cloud Data Engineer with 6+ years of overall experience, with a strong focus on building data solutions, cloud platforms, and increasingly, AI-powered applications.

My work sits at the intersection of Data Engineering, Cloud, Analytics, and Artificial Intelligence. I enjoy working with data from the ingestion layer all the way to analytics and AI applications, and I’m particularly interested in how modern AI can be connected with enterprise data to solve real-world problems.

I have experience designing and developing data pipelines and data platforms using cloud technologies across Azure, AWS, and GCP.

My experience includes:

• Microsoft Fabric
• Azure Data Factory
• Azure Databricks
• Azure Synapse Analytics
• Azure Data Lake
• Azure SQL
• Apache Spark & PySpark
• AWS data services
• Google Cloud data services
• Lakehouse and Medallion Architecture
• Batch and incremental data processing

I focus on building solutions that are scalable, maintainable, and practical for real business requirements.

Alongside data engineering, I’ve been working with Generative AI, LLMs, and Agentic AI and exploring how these technologies can be applied to data and enterprise use cases.

My areas of interest and hands-on work include:

• Large Language Models (LLMs)
• Generative AI applications
• Agentic AI
• AI Agents
• Tool calling and function calling
• RAG-based applications
• LLM integration with APIs and enterprise data
• Google ADK
• Azure OpenAI
• AI-powered data analysis and automation

What interests me most is not simply using an LLM to generate text, but building agents that can use tools, interact with data, make decisions, and perform multi-step tasks.

I enjoy turning raw and often messy data into something that can actually be used by analysts, applications, and business teams.

This includes:

• Data ingestion and integration
• Data cleansing and transformation
• Data modelling
• Data quality
• SQL-based analytics
• KQL
• Power BI
• Data warehousing
• Lakehouse solutions
• Performance optimization

I also have experience working with different types of data sources and integrating them into centralized cloud data platforms.

Good data solutions are not only about writing pipelines. They also need proper engineering practices.

I have experience with:

• Python
• SQL
• PySpark
• Git / GitHub
• Azure DevOps
• CI/CD
• REST APIs
• Metadata-driven pipelines
• Reusable frameworks
• Automation and monitoring

I prefer building reusable solutions rather than creating one-off pipelines that become difficult to maintain later.

I’m particularly interested in modern data architecture and how different technologies can work together.

Some of the areas I work with include:

Source Systems → Data Ingestion → Lakehouse → Transformation → Analytics → AI Applications

I enjoy understanding the complete flow rather than focusing on only one layer of the technology stack.

Technology is only one part of the job.

I regularly work with different stakeholders to understand requirements, discuss technical options, troubleshoot issues, and translate business problems into technical solutions.

I believe a good engineer should be able to explain a complex technical problem clearly and work with others to find a practical solution.

The data and AI ecosystem changes quickly, so I spend a lot of time experimenting with new technologies and building small proofs of concept to understand how they can be applied in real projects.

Currently, I’m particularly interested in the convergence of:

☁️ Cloud + 📊 Data Engineering + 🤖 AI + 🧠 Agentic Systems

I enjoy learning by building, experimenting, and sharing what I learn with the community.

📫 Feel free to connect with me: https://www.linkedin.com/in/achinta-mondal-04aa20131/

#DataEngineering #CloudDataEngineering #AgenticAI #GenerativeAI #LLM #AIAgents #MicrosoftFabric #Azure #AWS #GCP #ApacheSpark #PySpark #Python #SQL #PowerBI #DataAnalytics #CloudComputing #AI