Update README.md

README.md

@@ -11,10 +11,12 @@ pinned: false
 
 ## 🚀 Effortless and Secure Deployment of Large Language Models for Regulated Industries
 
-TitanML enables organizations in regulated industries to effortlessly and efficiently deploy large language models (LLMs). Our Titan Takeoff Inference Stack makes building, deploying, and scaling Generative AI applications in secure environments a breeze.
+[TitanML](https://titanml.co) enables organizations in regulated industries to effortlessly and efficiently deploy large language models (LLMs). Our Titan Takeoff Inference Stack makes building, deploying, and scaling Generative AI applications in secure environments a breeze.
 
 ### 🛫 Takeoff: The Fastest Way to LLM Inference
 
+Our [Titan Takeoff Inference Stack](https://www.titanml.co/takeoff-product) offers:
+
 - Lightning-fast local inference
 - Efficient batching support
 - Multi-GPU inference capabilities