Do you want to be part of the AGI organization and help build innovative applications leveraging the state of the art generative AI? Are you passionate about building scalable web services utilizing large language models? Do you believe that complex tasks can be achieved in an intuitive way?

Key job responsibilities
Build a scalable information grounding service that provides grounding evidence to multiple Amazonian experiences. Grounding large language models (LLMs) ensures that their interactions with users are informed, relevant, consistent, and trustworthy. It ensures accuracy and relevance by providing context-specific responses and mitigating the risk of generating false information through techniques like Retrieval-Augmented Generation (RAG). Grounding allows LLMs to adapt to rapid information changes without constant retraining, maintaining up-to-date and reliable outputs. This is accomplished by linking the models' outputs to verifiable sources of information retrieved from public web sources (e.g., WebIR) and other structured data sources (e.g., knowledge graphs, local databases). Grounding LLMs involves two main steps: 1/ providing relevant evidence from knowledge sources for the customer query and packing it into the LLM context window, and 2/ optimizing LLM (e.g., SFT, RLHF) to use this evidence appropriately, minimizing irrelevance or hallucinations.

Design & Write code: Write code primarily in Java and design scalable, fault tolerant and distributed applications running on AWS technology. Leverage state of the art AWS resources in the development of a scalable web grounding service for LLM based applications.

Test, test, test: Our software engineers don't just write code, they also test the heck out of it. You will write unit tests, integration tests and regression tests and find ways to automate them.

Troubleshoot and fix operational problems: You will work with systems engineers to troubleshoot operational problems and fix them. If you are so inclined, you will also automate troubleshooting procedures and write tools. And when the issues concern specific customers, you will also have the opportunity to talk to them and understand their space better.

Influence product direction: You will propose your ideas for the future of the space to product
management and get to shape the roadmap.

Hire and mentor others: You will get to interview people for the team and to mentor other engineers.