Backend Engineer - Copilot Memory and Personalization

Microsoft AI (Headquarters: Mountain View, California, United States)

Location: Mountain View, California, United States   |   Full-Time   |   $188,000 - $304,200
Backend Python Java C++ C# JavaScript Retrieval-Augmented Generation (RAG) Embeddings Ranking Microsoft AI Copilot Back End Engineer Data Science

About Microsoft AI:

Microsoft AI (MAI) is dedicated to advancing artificial intelligence technologies, building systems that have true artificial intelligence across various domains. Our work spans research, development, and productization, with a focus on making AI accessible to everyone. We’re currently building core infrastructure for Copilot Memory and Personalization, enabling long-term memory, intelligent search, and adaptive user experiences.

About The Role:

We are seeking a Backend Engineer to join our team building Copilot memory and personalization - AI that remembers, evolves, and grows with each user. You’ll work in a highly collaborative, fast-paced environment to develop systems that deepen memory with every interaction, personalize experiences, and make interactions feel more natural.

Responsibilities:

  • Design and build large-scale Copilot memory and personalization systems leveraging search, embeddings, retrieval, ranking, and Retrieval-Augmented Generation (RAG)
  • Apply subject-matter expertise in cross-product features, collaborating with stakeholders to drive project plans and deliverables
  • Hold accountability as a Designated Responsible Individual (DRI), mentoring engineers and monitoring system health
  • Proactively seek knowledge to improve product availability, reliability, efficiency, and performance
  • Navigate ambiguity and clear roadblocks to deliver solutions quickly and iteratively

Requirements:

  • Bachelor’s degree in computer science or related field AND 6+ years technical engineering experience with coding in languages like C, C++, C#, Java, JavaScript, or Python
  • 4+ years’ experience building APIs and creating pipelines for large-scale products
  • Experience building and deploying machine learning or large language model (LLM) applications at scale
  • Thrive in fast-paced, collaborative environments and are comfortable making progress in ambiguity
Post Date: July 29, 2025