Large Language Models (LLMs) are capable of human and super-human reasoning, but they don’t understand your personal or organizational data. The core mission of LlamaIndex is to enable developers to LLM-powered applications on top of any private data source.
We are at the forefront of a new way to build software. Doing this successfully will usher a new age of knowledge automation and completely redefine the modern data stack.
Our product offerings consist of an open-source Python/Typescript framework as well as an in-development enterprise platform. The framework has 1M+ monthly downloads and is used from large enterprises to early-stage startups - it is both easy to get started but robust for production use. We’re backed by Greylock and a fantastic set of angels, such as Jack Altman, Lenny Rachitsky, Mathilde Collin, Raquel Urtasun, Joey Gonzalez, Dan Shipper, Ben Tossell, and more.
Responsibilities: You will be responsible for architecting and scaling LlamaIndex’s cloud platform. You will work closely with our framework engineering and full-stack engineering team to deliver a top-notch integrated developer experience for building the next-generation of context-aware (i.e. RAG) applications.
Qualifications: You have a proven track record of building scalable cloud services that process massive amount of data. This include the full lifecycle of architecting scalable infrastructure, deploying containerized services to cloud providers via infrastructure-as-code. You are an expert at building quickly, but scale as necessary. You should know the in-and-out of building user-facing APIs. Prior experience with ETL / data orchestration / distributed data processing are strongly preferred.
You’re also passionate about LLMs and the immense opportunities it offers for developers and end users. You’re able to contextualize all backend decisions with the goal of creating an amazing set of tools for developers to use.
Benefits: