New: upload your resume and get matched to AI jobs. Free to start →

Senior Software Engineer, Foundry IQ - CoreAI

$120k - $235k • United States, Washington, Redmond; United States, California, Mountain View • Full-time

Posted 1mo ago

Job Location

United States, Washington, Redmond; United States, California, Mountain View

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Engineer

About the job

The Foundry IQ team is building the next generation of agentic knowledge retrieval, combining enterprise knowledge with AI agents at scale. We are expanding Azure AI Search to address complex queries that require refinement, reasoning, and reflection, delivering high-quality, grounded results for both people and large language models across a wide range of industries and mission-critical scenarios. In this role, you will design, build, and operate scalable backend services that integrate with internal and external language models, partner closely with Applied Science to turn research advances into reliable production capabilities, and develop GPU-backed integrations that support large-scale production machine learning workloads. You will evaluate end-to-end production systems to ensure the quality, reliability, and performance of AI-powered experiences, advance knowledge retrieval and data-layer AI integration, including RAG, agentic retrieval, and LLM context engineering, and determine where advanced reasoning models provide the most value. You will work directly with customers and partner teams to solve challenging retrieval and AI problems, collaborating with a multidisciplinary team of engineers, applied scientists, and product leaders across Microsoft.

Responsibilities

  • Design, build, and operate scalable backend services that integrate with internal and external language models.
  • Partner closely with Applied Science to turn research advances into reliable production capabilities.
  • Develop GPU-backed integrations that support large-scale production machine learning workloads.
  • Evaluate end-to-end production systems to ensure the quality, reliability, and performance of AI-powered experiences.
  • Advance knowledge retrieval and data-layer AI integration, including RAG, agentic retrieval, and LLM context engineering.
  • Determine where advanced reasoning models provide the most value and integrate low-latency models where speed is critical.
  • Work directly with customers and partner teams to solve challenging retrieval and AI problems.
  • Design, build, and maintain Azure backend services and associated APIs.
  • Bring high quality prompts, ML models and pre and post processing components into production in a secure, reliable, and scalable way.
  • Provide evaluation tooling and support of production integrations to ensure end-to-end AI quality of Applied Science deliverables.
  • Contribute to team plans, documents, and communication in a clear and efficient way.

Requirements

  • Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.
  • Strong distributed-systems experience.
  • Practical expertise in machine learning infrastructure.
  • Experience with GPU-hosted model integration.
  • Experience with LLM context engineering.
  • Comfortable partnering with Applied Science.
  • Ability to navigate ambiguous technical challenges.
  • Ability to translate emerging AI capabilities into secure, dependable, and low-latency services at cloud scale.
  • Development of Azure Services with full understanding of service release and live-site responsibilities.
  • Coding in C# and Python in a production system.
  • Ability to move fast while ensuring quality at scale in a collaborative team setting.
  • Development experience with large language models.
  • Development experience with GPU based models and model hosting.
  • 2+ years’ experience developing and deploying live production systems as part of a product team.
  • Coding in C++ or Java in a production system.
  • Excellent hybrid work skills – clear synchronous and asynchronous communication, strong teamwork, and collaboration skills.
  • Customer focused, strategic, drives for results, is self-motivated, and has a propensity for action.
  • Ability to solve problems that the world has not solved before.

Benefits

  • Base pay range: USD $119,800 - $234,700 per year (US)
  • Base pay range: USD $160,200 - $261,000 per year (San Francisco Bay area and New York City metropolitan area)
  • Certain roles may be eligible for benefits and other compensation.