Our Client, a Media, Information and Services company, is looking for a Senior Copilot & Azure AI Foundry Engineer for their Charlotte, NC location.
Responsibilities:
Copilot Optimization:
Analyze and refactor Copilot Studio agents to eliminate redundancies, improve routing efficiency, and streamline topic structures for better maintainability.
Generative AI Modernization:
Transition static, rule-based topics into grounded generative experiences and replace legacy ingestion methods with modern Azure AI approaches.
Advanced RAG Implementation:
Enhance solution accuracy by integrating Azure AI Foundry capabilities, including Cognitive Search with vector embeddings and custom RAG endpoints.
Sophisticated AI Features:
Implement high-level capabilities like multi-step reasoning, context persistence, summarization, and function calling for complex user interactions.
End-to-End MLOps:
Design and manage scalable AI/ML pipelines, covering everything from model fine-tuning and versioning to CI/CD, monitoring, and security.
Architectural Leadership:
Serve as the technical lead to design scalable architectures, guiding best practices and ensuring internal teams can maintain the solution post-handoff.
Operational Enablement:
Develop infrastructure-as-code for resilient workloads and produce comprehensive documentation, including troubleshooting guides and operational playbooks.
Requirements:
8+ years in software architecture or cloud engineering, with at least 3+ years specifically focused on production-grade AI/ML solutions.
AI Ecosystem:
Strong hands-on experience with Microsoft Copilot Studio and Azure AI Foundry (formerly Azure AI Studio).
Technical Proficiency:
Expert-level Python for AI/ML development and automation; additional experience in C#, .NET, or Java is preferred.
AI Specialization:
Solid understanding of Generative AI, prompt engineering, RAG architectures, embeddings, and vector databases.
MLOps & DevOps:
Demonstrated experience with model lifecycle management, CI/CD pipelines, and designing resilient, serverless AI workloads.
Problem Solving:
Proven ability to troubleshoot, refactor, and optimize existing AI solutions to meet 99.8% accuracy targets.
Soft Skills:
Ability to lead architectural discussions with executive stakeholders and translate business needs into technical AI requirements.