AI Language Engineer II, Alexa for Shopping Lang-Tech
The Conversational Shopping team is looking for an AI Language Engineer to drive innovation and scalable solutions as it delivers a delightful AI-assisted shopping experience. This is an opportunity to join the high-performing org behind Alexa for Shopping. Our objective is to make it easy for customers to find and discover the best products for their unique needs through recommendations, comparisons, product Q&A, and more. This role is cross-functional, requiring collaboration across global product, design, science, and engineering teams.
We are looking for candidates who are passionate about the intersection of language and technology and who are keen to use their technical abilities to develop automated, scalable solutions to challenges in the Large Language Model (LLM) space. Applying a combination of expertise in LLMs, coding, and natural language, they will overcome complex problems in model evaluation, automation, and context engineering for agentic systems.
In this role within the AI Shopping org, they will contribute to our evaluation-driven product development strategy. They will work in close collaboration with Product Managers, Applied Scientists, Software Engineers, UX Researchers, and Editors on initiatives that drive quality, speed and consistency. They will be responsible for authoring, optimizing, and managing system prompts for customer-facing AI driven shopping experiences on both the mobile and web apps. They will define requirements for internal tooling by developing prototypes. They will employ their data processing and analysis skills to evaluate and report on model performance, producing insights that inform product decisions. By creating and synthesizing quality metrics, they will also support Conversational Shopping teams in delivering both internal stakeholder requirements and achieve the desired Amazon customer outcomes.
This role requires strong analytical and technical skills as well as experience in language technology to help us measure, analyze and solve complex problems. The candidate should have experience in creating technical solutions for automating and processing data workflows at scale and have the ability to do so while upholding the highest linguistic quality standards. They should also have exceptional writing and communication skills with the ability to interface between both technical and non-technical teams.
Key job responsibilities
- Develop LLM-as-a-judge systems to support Human-in-the-loop evaluations
- Automate operations and perform data analysis using scripting languages (e.g. Python)
- Author, optimize, and manage system prompts for customer-facing LLM systems
- Integrate API calls into Retrieval Augmented Generation (RAG) systems
- Evaluate model performance and annotation quality to produce reports for stakeholders
- Produce, process, and manipulate different types of language data
- Contribute to defining platform requirements for internal tooling by developing prototypes
- Raise the quality bar on editorial workflows and SOPs through standardization, documentation, and periodic audits and investigations
- Support processes and mechanisms to onboard and upskill Editors and AI Tutors on an ongoing basis
- Design, implement, and refine control mechanisms, metrics, and methodologies to ensure editorial and annotation quality
- Collaborate with editors, applied scientists, engineers, and product managers to deliver an optimal customer experience by defining metrics, guidelines, and workflows
- Deliver across parallel workstreams, balancing timelines, impact, and stakeholder requirements
About the team
The CMX-Lang-Tech team is a technical sub-team of the AI Shopping Content team. We are responsible for AI response quality both in terms of evaluating and prompting our AI models.
We are looking for candidates who are passionate about the intersection of language and technology and who are keen to use their technical abilities to develop automated, scalable solutions to challenges in the Large Language Model (LLM) space. Applying a combination of expertise in LLMs, coding, and natural language, they will overcome complex problems in model evaluation, automation, and context engineering for agentic systems.
In this role within the AI Shopping org, they will contribute to our evaluation-driven product development strategy. They will work in close collaboration with Product Managers, Applied Scientists, Software Engineers, UX Researchers, and Editors on initiatives that drive quality, speed and consistency. They will be responsible for authoring, optimizing, and managing system prompts for customer-facing AI driven shopping experiences on both the mobile and web apps. They will define requirements for internal tooling by developing prototypes. They will employ their data processing and analysis skills to evaluate and report on model performance, producing insights that inform product decisions. By creating and synthesizing quality metrics, they will also support Conversational Shopping teams in delivering both internal stakeholder requirements and achieve the desired Amazon customer outcomes.
This role requires strong analytical and technical skills as well as experience in language technology to help us measure, analyze and solve complex problems. The candidate should have experience in creating technical solutions for automating and processing data workflows at scale and have the ability to do so while upholding the highest linguistic quality standards. They should also have exceptional writing and communication skills with the ability to interface between both technical and non-technical teams.
Key job responsibilities
- Develop LLM-as-a-judge systems to support Human-in-the-loop evaluations
- Automate operations and perform data analysis using scripting languages (e.g. Python)
- Author, optimize, and manage system prompts for customer-facing LLM systems
- Integrate API calls into Retrieval Augmented Generation (RAG) systems
- Evaluate model performance and annotation quality to produce reports for stakeholders
- Produce, process, and manipulate different types of language data
- Contribute to defining platform requirements for internal tooling by developing prototypes
- Raise the quality bar on editorial workflows and SOPs through standardization, documentation, and periodic audits and investigations
- Support processes and mechanisms to onboard and upskill Editors and AI Tutors on an ongoing basis
- Design, implement, and refine control mechanisms, metrics, and methodologies to ensure editorial and annotation quality
- Collaborate with editors, applied scientists, engineers, and product managers to deliver an optimal customer experience by defining metrics, guidelines, and workflows
- Deliver across parallel workstreams, balancing timelines, impact, and stakeholder requirements
About the team
The CMX-Lang-Tech team is a technical sub-team of the AI Shopping Content team. We are responsible for AI response quality both in terms of evaluating and prompting our AI models.