Design, build, and operate scalable AI systems that power intelligent product experiences, including Copilot and agent-driven workflows. Architect and implement backend services that support multi-step AI interactions, including orchestration pipelines, context management, memory/state persistence, and tool execution. Evaluate, benchmark, and tune AI/ML models (LLMs and traditional models) to meet product requirements for accuracy, latency, reliability, and safety. g. , RAG systems, semantic ind…
Responsibilities
Integrate large language models (LLMs), APIs, and internal services to enable context-aware, human-in-the-loop experiences across customer scenarios. Build and maintain data and inference pipelines that support model training, fine-tuning, evaluation, and real-time inference across diverse data sources. Implement robust retrieval, grounding, and knowledge integration mechanisms (e. Collaborate with product managers, software engineers, and researchers to translate product vision into production-ready AI capabilities and measurable outcomes. Ensure reliability, observability, and governance of AI systems, including monitoring model performance, data quality, and responsible AI practices. Build reusable platforms, APIs, and tools that enable teams to rapidly develop AI-powered features and self-service intelligent applications.
Required Qualifications
12+ years of experience in software engineering, with significant experience building scalable backend or distributed systems. Strong programming expertise in one or more languages such as Python, Go, Java, or C#, with experience designing production-grade services and APIs. Experience building AI-powered applications, including integrating LLMs, implementing agent or Copilot workflows, and orchestrating multi-step AI interactions. Experience evaluating and improving model performance through prompt design, evaluation frameworks, fine-tuning, or feedback loops. Experience deploying and operating AI workloads in cloud environments (preferably Azure), including containerized services and GPU-enabled infrastructure. Ability to work across product, research, and engineering teams to translate product scenarios into scalable AI system architectures.
Original Posting
This role is sourced from Microsoft. Apply on Microsoft careers page