Design and build scalable architectures based on Large Language Models (LLMs), integrating with external data sources and APIs, with a focus on Retrieval-Augmented Generation (RAG) systems.
Develop complex LLM workflows, incorporating multiple models, data sources, and processing steps.
Implement and maintain CI/CD pipelines for efficient and reliable deployment and updates.
Establish and manage cloud-based infrastructure tailored for LLM applications.
Conduct vigilant monitoring of LLM performance and resource utilization.
Automate testing and quality assurance processes to maintain the highest standards of LLM accuracy and reliability.
Required Skills
Expertise in LLM frameworks, with a particular emphasis on RAG systems such as LLamaIndex and Langchain.
Hands-on experience with Large Language Models like GPT-3/4, Llama 3x, Claude, PaLM, and their APIs.
Strong background in system design and the construction/deployment of LLM-based applications.
Proficiency in DevOps and LLMOps, including CI/CD pipelines, cloud platforms, and monitoring tools.
BS in CS, Math, Data Science or related field. MS preferred.
