Excelsior Design

MUST BE A U.S CITIZEN

POSITION IS FULLY REMOTE, BUT INTERVIEW PROCESS WILL REQUIRE AN IN-PERSON INTERVIEW IN LAS VEGAS, AT THE CANDIDATE'S EXPENSE.

DO NOT APPLY IF YOU DO NOT MEET/AGREE WITH THE STATEMENTS ABOVE.

THANK YOU!

Overview
We are seeking a highly skilled and innovative AI Solutions Developer to design, build, and deploy a secure, on-premises AI system focused on document indexing and intelligent query answering. This role requires deep expertise in the .NET framework and Elasticsearch, specifically leveraging Retrieval-Augmented Generation (RAG) or Model Context Protocol (MCP) architectures to ground multiple Large Language Models (LLMs) in proprietary enterprise data. The ideal candidate will ensure the system provides accurate, context-aware, and secure responses within a controlled, on-premises environment.

Responsibilities

• System Design & Architecture: Architect scalable and efficient on-premise RAG systems using .NET technologies (C#, ASP.NET) and Elasticsearch as the primary vector database and search engine.
• Document Indexing & Data Pipelines: Design and implement robust data ingest pipelines to process, embed, and index large volumes of structured and unstructured documents into Elasticsearch clusters.
• RAG/MCP Implementation: Develop and optimize RAG pipelines, making strategic decisions on document chunking, embedding models, and retrieval mechanisms to balance precision, recall, and latency.
• LLM Integration & Management: Integrate and manage multiple LLM models (local or private/secure APIs) to generate contextually relevant and accurate answers based on retrieved documents.
• Performance Optimization & Tuning: Monitor and optimize the performance of Elasticsearch clusters, query execution, and AI system performance, ensuring high availability and data integrity in an on-premises setting.
• Security & Compliance: Implement robust security controls and ensure the system adheres to on-premises data security and compliance policies.
• Collaboration & Documentation: Work closely with cross-functional teams (operations, product management, cyber security) and create comprehensive technical documentation for system design, development, and maintenance.

Required Qualifications and Skills

• Strong background in software development using the .NET framework and C#.
• Proven experience with Elasticsearch (design, administration, performance tuning, indexing, mapping).
• Hands-on experience in building and deploying RAG systems.
• Familiarity with alternative agentic frameworks or the Model Context Protocol (MCP) is a strong advantage.
• Experience with vector databases and embedding models (e.g., OpenAI, Hugging Face models, or private/local alternatives).
• Proficiency in languages like Python (for AI/ML scripting/tooling) or Java (Elasticsearch's core) to integrate with the core backend is necessary.

Experience:

• Prior experience in deploying and managing software and AI/ML systems in on-premises or hybrid cloud environments.
• Experience working with large datasets and document processing workflows.
• Experience with multi-agent orchestration or managing multiple AI models is a plus.

Soft Skills:

• Strong analytical and problem-solving abilities.
• Excellent communication skills and the ability to collaborate effectively in a team environment.
• High degree of autonomy and ability to lead projects from design to production.

Job Types: Full-time, Contract, Temporary

Pay: $60.00 - $75.00 per hour

Experience:

• AI models: 7 years (Required)
• .NET: 7 years (Required)
• Elasticsearch: 7 years (Required)
• RAG : 7 years (Required)

Work Location: Remote