AI Engineer
As an AI Engineer, my focus is on designing, developing, and maintaining AI models and systems to tackle challenges and enhance decision-making within organizations. I have a deep interest in scalable architecture, DevOps pipelines, efficient programming, code quality, and best practices. On this page, I aim to share insights, tutorials, and some unique discoveries that might not be easily found elsewhere, all of which reflect my journey and learning in the field.
My Current Interests
Automated AWS Deployment
Automate the deployment of resources across multiple accounts and regions using a pipeline, ensuring efficient setup for both development and production environments. This approach supports consistent configurations, integrates with CI/CD processes, and includes rollback capabilities for improved stability.
LangChain
LangChain is a comprehensive framework enabling the development of context-aware and reasoning-driven applications powered by language models, supported by Python and JavaScript libraries, templates, and deployment tools.
My focus lies in understanding the RAG pipeline intricately, while also constructing chains of prompts to develop complex generative AI tools.
Ragas
Ragas is a tool designed to assess and quantify the performance of Retrieval Augmented Generation (RAG) pipelines, which enhance language model applications by incorporating external data into their context.
I find immense value in evaluating RAG pipelines to transform prompt engineering into a more scientific and data-driven practice.
Newest Insights & Stories
Creating and Deploying Custom Lambda Layers for Python Functions
September 2, 2024
A step-by-step guide on creating and deploying custom AWS Lambda layers to include additional Python dependencies, featuring a bash script for building layers locally.
Read more
AWS Python Lambda Timeout Handler
August 2, 2024
Learn how to handle AWS Python Lambda timeouts effectively using a timeout handler to manage long-running processes and ensure seamless execution, even past the 15-minute limit.
Read more
Building a GenAI-powered Excel Add-in - Part 03 - Backend Integration
May 10, 2024
In Part 3 of the tutorial, learn how to build and integrate a backend server using FastAPI and Python, and connect them to our Frontend.
Read more