Skip to main content

🗓️ Monthly Review - 2025

Reflecting on my journey through a monthly review, where I meticulously scrutinize past achievements and endeavors. This process isn't just about accountability; it's a strategic examination that unveils valuable insights into my professional evolution.

 

January - 2025​

  • Implemented logging response time for all the API calls made to other services to monitor latency.
  • Created new DynamoDB table for storing user support details and migrated block counts.
  • Integrated new HMAC(Hash-based Message Authenticated Code) API.
  • Deployed Meta's Large Language Model, Llama 3.2, on AWS Bedrock and built AI writing assistant for agents.

February - 2025​

  • Designed and built independenlty DAZN's first Large Language Model(LLM) application, leveraging generative AI with Retrieval Augmented Generation(RAG) using Vector Search, that provides real time analysis of customer support queries, therefore helping operations team derive strategies to resolve them quickly.
  • Built Yoga Pose Recommender: AI-Powered Vector Search for Yoga Poses, an AI-powered semantic search system that helps users explore yoga poses. By leveraging Gemini (LLM) to generate rich, context-aware descriptions and create high-dimensional vector embeddings, the project transforms an existing Hugging Face dataset into a deeply intelligent and intuitive search experience. With LangChain JS orchestrating data processing and Firestore serving as a high-performance vector database, users can retrieve the most relevant yoga poses through natural language queries. Additionally, Google Cloud’s Text-to-Speech technology enhances accessibility by providing immersive audio descriptions. Built with Node.js, this system seamlessly integrates AI-driven search, vector embeddings, and real-time query processing to redefine yoga exploration.