Senior Software Engineer, Foundry IQ - CoreAI

Microsoft•Redmond, WA

1d•$119,800 - $234,700

About The Position

The Foundry IQ team is building agentic knowledge retrieval by combining enterprise knowledge with AI agents at scale. The team is expanding Azure AI Search to handle complex queries that require refinement, reasoning, and reflection, delivering high-quality, grounded results for people and large language models across a wide range of industries, data volumes, and mission-critical scenarios. In this role, you will build and operate scalable Azure backend services and APIs that integrate with internal and external language models. You will work closely with Applied Science to bring research advances, prompts, machine-learning models, and pre- and post-processing components into secure, reliable, scalable production systems. The work includes GPU-backed integrations for production machine-learning workloads, evaluation tooling for end-to-end AI quality, and advances in knowledge retrieval and data-layer AI integration, including RAG, agentic retrieval, and LLM context engineering. You will help determine where advanced reasoning models are most valuable and integrate low-latency models where speed is critical. You will collaborate with engineers, applied scientists, product leaders, and teams across Microsoft, including Bing, Fabric, Work IQ, and Microsoft Research. The role involves addressing challenging retrieval and AI problems with customers and partner teams, contributing to team plans and documentation, and translating emerging AI capabilities into dependable, low-latency services at cloud scale.

Requirements

Bachelor’s degree in Computer Science or a related technical field and 4+ years of technical engineering experience coding in languages including C, C++, C#, Java, JavaScript, or Python, or equivalent experience.
Ability to meet Microsoft, customer, and/or government security screening requirements, including passing the Microsoft Cloud Background Check upon hire or transfer and every two years.
Strong distributed-systems experience and practical expertise in machine-learning infrastructure, GPU-hosted model integration, and LLM context engineering.
Ability to partner with Applied Science, navigate ambiguous technical challenges, and translate emerging AI capabilities into secure, dependable, low-latency services at cloud scale.

Nice To Haves

Experience developing Azure services, including understanding service release and live-site responsibilities.
Production-system coding experience in C# and Python.
Ability to move quickly while ensuring quality at scale in a collaborative team setting.
Experience developing with large language models.
Experience developing GPU-based models and model hosting.
2+ years of experience developing and deploying live production systems as part of a product team.
Production-system coding experience in C++ or Java.
Strong hybrid-work skills, including clear synchronous and asynchronous communication, teamwork, and collaboration.
Customer focus, strategic thinking, results orientation, self-motivation, and propensity for action.
Problem-solving ability, including solving problems that have not been solved before.

Responsibilities

Design, build, and maintain Azure backend services and associated APIs.
Partner with Applied Science to bring high-quality prompts, machine-learning models, and pre- and post-processing components into production securely, reliably, and at scale.
Work directly with GPUs to support production machine-learning workloads at scale.
Provide evaluation tooling and support production integrations to ensure the end-to-end quality of Applied Science deliverables.
Contribute clearly and efficiently to team plans, documents, and communications.
Work with customers and partner teams to solve challenging retrieval and AI problems.
Develop knowledge retrieval and data-layer AI integrations, including RAG, agentic retrieval, and LLM context engineering.
Evaluate production systems for the quality, reliability, and performance of AI-powered experiences.