Laptop on a rocky beach. Photo by Dean Pugh on Unsplash.
Ardee Aram

Ardee Aram

Software Engineer - Python / Rails / AWS / Machine Learning
Get In Touch

👨🏻‍💻 3x Amazon Web Service (AWS) Certified Software Engineer 👨‍👩‍👦‍👦 Husband, and dad of two 🧘🏾 Eternal student of life

Serverless AI: Deploy Hugging Face Models on SageMaker for Less Than the Cost of a Burger

Serverless AI: Deploy Hugging Face Models on SageMaker for Less Than the Cost of a Burger

A Step-by-Step Guide on Deploying and Hosting Hugging Face 🤗 Models on AWS SageMaker Serverless

How to make a Retrieval Augmented Generation (RAG) solution quickly with Amazon Bedrock and Django

How to make a Retrieval Augmented Generation (RAG) solution quickly with Amazon Bedrock and Django

Let's build a simple RAG solution using Bedrock and Django. This is a great introductory project when trying to learn more about Large Language Models and AI Integration.

How to deploy Django on AWS Lambda

How to deploy Django on AWS Lambda

How to host a Django 5 project for a few cents per month?

Where do I host my Django 5 projects for free?

Where do I host my Django 5 projects for free?

Vercel surprisingly offers free Django 5 hosting for low-traffic sites. Read on to learn how.

Serverless apps: The startup founder's secret weapon

Serverless apps: The startup founder's secret weapon

 • 

How can you build web scale apps on a shoestring budget?

Safelink ML Python Rails

AI-enabled secure file sharing for lawyers
Safelink

Ask Alex LLM ML RAG

Data interrogation for law professionals
Ask Alex

Abogado PH LLM Python RAG

AI-Powered Legal Insights for Philippine Laws
Abogado PH
April fools bring May hallucinations

April fools bring May hallucinations 

No, Grok didn’t just solve a legendary math problem. But it gets worse.

Text summarization with Amazon SageMaker and Hugging Face | Amazon Web Services

Text summarization with Amazon SageMaker and Hugging Face | Amazon Web Services 

In this post, we show you how to implement one of the most downloaded Hugging Face pre-trained models used for text summarization, DistilBART-CNN-12-6, within a Jupyter notebook using Amazon SageMaker and the SageMaker Hugging Face Inference Toolkit. Based on the steps shown in this post, you can try summarizing text from the WikiText-2 dataset managed […]

Deploy models with Amazon SageMaker Serverless Inference - Amazon SageMaker AI

Deploy models with Amazon SageMaker Serverless Inference - Amazon SageMaker AI 

Deploy and scale ML models without configuring or managing any of the underlying infrastructure with Amazon SageMaker Serverless Inference.

DeepSeek-R1 now available as a fully managed LLM model in Amazon Bedrock

DeepSeek-R1 now available as a fully managed LLM model in Amazon Bedrock 

AWS expands the ways that customers can get started with DeepSeek-R1 and its distilled variants in Amazon Bedrock.