◦ Initiated major enhancement by adding support for Llama2 Model; streamlined OpenAI
APIs to respond to user queries and answering technical questions from Slack,
and Whatsapp
◦ Designed a new handler to process 10,000+ concurrent requests/s leveraging OpenAI
and HuggingFace interface
◦ Optimized response time from minutes to seconds by quantization,
asynchronous inference, and caching
◦ Experienced Technical Writer, authored multiple blogs revealing complex technical concepts to a broader audience in a simple manner.
Like this project
Posted Dec 26, 2023
Built multiple integrations like Llama2, Slack, Whatsapp, etc. Performed Unit Tests. Authored Technical Blogs. Worked on community growth.