AI Engineer - Enterprise AI Agents & Microsoft Fabric Integration

AI Engineer - Enterprise AI Agents & Microsoft Fabric Integration -

Remote

Position Overview

Join our cutting-edge AI initiative to build intelligent agents that seamlessly integrate with our Microsoft Fabric Data Lake as the central data hub, connecting structured data from Infor M3 ERP, Salesforce CRM, Anaplan planning platform, Uncountable PLM, and Freshworks help desk alongside unstructured data from SharePoint, file systems, and document repositories. We're seeking an AI Specialist to architect next-generation agents that understand and interact with complex business processes by leveraging our unified data architecture. This role involves creating sophisticated RAG systems, vector databases, and multi-modal AI capabilities that transform how our organization leverages both structured enterprise data and unstructured content across all touchpoints - from manufacturing and supply chain to customer relationships and product lifecycle management.

Key Responsibilities:

AI Agent Architecture

Design agents connecting primarily to Microsoft Fabric Data Lake as central data repository
Access structured data from Infor M3 ERP, Salesforce CRM, Anaplan, Uncountable PLM, and Freshworks stored in Fabric
Process unstructured data from SharePoint, file systems, and document repositories outside Fabric
Implement RAG systems using FAISS, Pinecone, Weaviate, ChromaDB for hybrid structured/unstructured search
Build natural language interfaces for querying both lakehouse tables and external document sources
Create unified data processing pipelines combining Fabric data with external unstructured content
System Integration & Data Processing

Connect to Microsoft Fabric Data Lake using Delta Lake format and SQL endpoints
Access structured business data from all enterprise systems centralized in Fabric lakehouse
Integrate unstructured data sources: SharePoint documents, file servers, email archives
Process PDFs, Word docs, Excel files, images, and multimedia content from external systems
Implement real-time data streaming from Fabric Event Streams and external file monitoring
Build hybrid search capabilities combining Fabric structured data with external document vectors
Multi-Platform AI Development

Utilize OpenAI GPT-4, Anthropic Claude, Google Gemini, Meta LLaMA, and Cohere APIs Implement model routing and fallback strategies across AI providers
Build agents using LangChain, LlamaIndex, AutoGen, CrewAI frameworks
Deploy containerized solutions with Docker/Kubernetes for scalability

Required Skills:

Core Technical Expertise:

5+ years AI/ML development with enterprise data integration
3+ years Microsoft Fabric, Azure Data Lake, or similar lakehouse platforms
Advanced Python with AI/ML libraries (LangChain, LlamaIndex, Transformers)
SQL/KQL proficiency for complex data querying and analysis
Vector database expertise (FAISS, Pinecone, Weaviate, ChromaDB)
RAG system architecture and implementation at enterprise scale
AI & Machine Learning

Multi-LLM integration (OpenAI, Anthropic, Google, Cohere APIs) Prompt engineering and advanced AI agent orchestration Embedding models and semantic search optimization Fine-tuning experience with domain-specific models AI safety and governance implementation
Enterprise Integration

Microsoft Fabric Data Lake and Delta Lake architecture SharePoint API integration and document processing RESTful API design and microservices architecture Real-time data streaming and event-driven systems Enterprise security and authentication (OAuth, SSO)
Development & Deployment

Full-stack development (React/Angular frontend, FastAPI/Node.js backend)
Cloud platforms (Azure preferred, AWS/Google Cloud Platform experience valued)
Containerization (Docker, Kubernetes) and DevOps practices
CI/CD pipelines and automated testing frameworks
AI Platform Experience

Multiple LLM providers (OpenAI, Anthropic, Google, Cohere) for text and multimodal processing
Vector databases (FAISS, Pinecone, Weaviate, ChromaDB) for semantic search across business data
Document processing tools (PyPDF2, PDFplumber, Tesseract OCR, Azure Document Intelligence)
Integration frameworks for Infor M3, Salesforce, Anaplan, Uncountable PLM, and Freshworks
Frontend frameworks (React, Angular, Vue.js) and backend (FastAPI, Django, Node.js)
Data Platform Knowledge

Microsoft Fabric Data Lake, Delta Lake, and lakehouse architecture expertise
Structured data access from Fabric tables containing ERP, CRM, and planning data
SharePoint integration for document libraries and collaborative content
File system monitoring and processing for external unstructured data sources
Azure Data Factory and Fabric Data Factory for ETL/ELT pipelines
Power BI integration for data visualization and reporting within Fabric ecosystem
Preferred Qualifications & Certifications

Microsoft Fabric Analytics Engineer or Azure AI Engineer Associate certification
Bachelor's/Master's degree in Computer Science, AI/ML, or related field
Enterprise AI implementation experience in manufacturing or finance
Apache Spark and big data processing experience
Power BI development and advanced analytics
Agile/Scrum methodology and cross-functional team collaboration
Technical leadership and mentoring experience
Technology Stack

AI/ML: OpenAI, Anthropic Claude, Google Gemini, Hugging Face, LangChain, LlamaIndex Vector DB: FAISS, Pinecone, Weaviate, ChromaDB, Qdrant Data Platform: Microsoft Fabric Data Lake, Delta Lake, Azure Data Factory, Power BI Structured Data: ERP, CRM, PLM, helpdesk data centralized in Fabric lakehouse Unstructured Sources: SharePoint, file systems, document repositories, email archives Integration: Fabric APIs, REST APIs, GraphQL, webhooks, Microsoft Graph API Development: Python, JavaScript, KQL, SQL, React, FastAPI, Docker, Kubernetes