Generative AI Engineer at Ampcus Inc Generative AI Engineer at Ampcus Inc in Annandale, Virginia Posted in 1 day ago.

Type:

full-time Experience 3-8 Years Role Overview We are seeking a highly skilled MCP (Model Context Protocol), RAG (Retrieval-Augmented Generation), and Connectors Engineer to design, build, and optimize AI-powered solutions that integrate enterprise data sources with Large Language Models (LLMs). The ideal candidate will have hands-on experience with AI platforms, enterprise integrations, vector databases, retrieval pipelines, APIs, and modern AI application architectures. The role will focus on enabling secure, scalable, and context-aware AI experiences by developing MCP servers, building RAG pipelines, and integrating enterprise systems through custom connectors. Key Responsibilities MCP (Model Context Protocol) Design and develop MCP servers and tools for LLM-driven applications. Implement tool-calling frameworks and agent integrations. Enable secure exposure of enterprise capabilities to AI assistants. Manage authentication, authorization, and governance of MCP services. Optimize context-sharing mechanisms between AI models and enterprise systems. RAG Engineering Design and implement enterprise-grade RAG architectures. Build document ingestion, chunking, embedding, indexing, and retrieval pipelines. Integrate vector databases and semantic search solutions. Improve answer quality through reranking, hybrid search, and prompt optimization. Monitor retrieval accuracy, latency, and hallucination rates. Evaluate and implement advanced retrieval techniques. Connectors & Integrations Develop connectors for enterprise systems such as: Point Microsoft Graph Azure Storage Salesforce ServiceNow SAP Databases (SQL/NoSQL) Internal APIs Build API integration frameworks and data synchronization pipelines. Implement event-driven and real-time data access patterns. Ensure scalability, security, and data compliance requirements. AI Platform Development Collaborate with Data Scientists, AI Engineers, and Product Teams. Build reusable AI integration frameworks and SDKs. Develop observability, monitoring, and governance solutions. Implement CI/CD pipelines for AI services. Support production deployment and operational excellence. Required Skills

AI & LLM

Technologies Strong understanding of Large Language Models (GPT, Claude, Gemini, Llama, etc.) Hands-on experience with: LangChain LlamaIndex Semantic Kernel Azure AI Foundry / Azure OpenAI AI Agents and Tool Calling RAG Expertise Embeddings and vector search Semantic search and hybrid retrieval Metadata filtering Document processing pipelines Evaluation frameworks for RAG systems MCP Knowledge Understanding of MCP architecture and ecosystem MCP server development and tool registration Context management and agent integration Integration Development REST APIs GraphQL APIs OAuth 2.0 / OpenID Connect Microsoft Graph API Enterprise system integration patterns Programming Skills Python (mandatory) JavaScript / TypeScript FastAPI, Flask, Node.js SDK and API development Data & Search Technologies Azure AI Search Pinecone Weaviate Chroma Elasticsearch / OpenSearch SQL and NoSQL databases Cloud Platforms Microsoft Azure (preferred) AWS or Google Cloud (good to have) Docker and Kubernetes CI/CD pipelines Preferred Qualifications Experience building Microsoft Copilot extensions and plugins. Experience with Copilot Studio and Microsoft Graph Connectors. Understanding of enterprise security and governance frameworks. Exposure to Agentic AI and multi-agent architectures. Knowledge of MLOps and AI observability tools. Azure AI Engineer, Azure Developer, or related certifications. Success Metrics Improved retrieval accuracy and response quality. Reduced AI hallucinations through optimized RAG pipelines. Successful integration of enterprise data sources. High availability and performance of MCP services. Adoption of AI solutions across business functions. Nice-to-Have Experience Microsoft 365 Copilot extensibility Graph Connectors Azure AI Search Copilot Studio OpenTelemetry Prompt Engineering Multi-Agent Systems Knowledge Graphs Event-Driven Architectures