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.
BASIC QUALIFICATIONS
- 3+ years of non-internship professional software development experience
- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience programming with at least one software programming language
PREFERRED QUALIFICATIONS
- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Bachelor's degree in computer science or equivalent
Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
Our compensation reflects the cost of labor across several US geographic markets. The base pay for this position ranges from $129,300/year in our lowest geographic market up to $223,600/year in our highest geographic market. Pay is based on a number of factors including market location and may vary depending on job-related knowledge, skills, and experience. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, please visit https://www.aboutamazon.com/workplace/employee-benefits. This position will remain posted until filled. Applicants should apply via our internal or external career site.