At Nosible I have worked on large scale custom semantic search, classic natural language processing tasks and deploying open-source large language models (LLMs) onto large GPU servers. I have worked on using Retrieval augmented generation (RAG) pipelines using LLM providers such as OpenAI and frameworks like Langchain to perform question answering. I have also built quantitative finance factor models and a backtesting engine where you can test strategies based on multi-factor models.