Experteer Overview Join the Bing Metrics team to shape the next generation of search quality using Retrieval-Augmented Generation (RAG) and LLMs. You will design metrics, build data pipelines, and create tools to evaluate and improve Bing Grounding quality across APIs and search experiences. Collaborate across ~80 teams to influence relevance and user experience at scale. This role combines ML, data engineering, and prompt engineering to deliver actionable insights for cross-functional teams. You’ll work in a high-visibility, collaborative environment that values growth and impact.Compensaciones / Beneficios - Design and implement RAG metrics for Bing Web Search and related APIs - Build end-to-end data pipelines and dashboards to monitor grounding quality - Apply LLMs as judges to evaluate data across queries, answers, and pages - Engineer prompts for textual and multi-model LLMs to process data and generate insights - Develop end-to-end pipelines from log anomaly sampling through prompt engineering to updatable dashboards - Combine classical ML (feature engineering, model training, embeddings) with LLMs for data analysis - Support cross-team efforts to innovate search experiences on BingResponsabilidades - Bachelor's degree in Statistics, Econometrics, Computer Science, Electrical Engineering, or Computer Engineering (or equivalent experience) - Experience with relational and/or non-relational databases;
proficient in SQL or equivalents - Experience developing and applying LLMs, including Retrieval-Augmented Generation (RAG) techniques - Ability to work independently and collaborate effectivelyRequisitos principales -