Part-Time AI Engineer (RAG)

Job Summary

We are looking for a hands-on Part-Time AI Engineer to develop and maintain an enterprise AI document search and knowledge management platform.

The role focuses on RAG, vector search, local LLM integration, ACL-based document access, automated indexing, and MCP integration with OpenText CS and enterprise workflows.

Most work can be performed remotely. However, the candidate will be required to work on-site approximately 2–3 times per month, with each on-site session lasting around half a day.

Job Scope

• Design, develop, and deploy an AI-powered enterprise document search and RAG system.
• Implement ACL to ensure users can only access authorized documents.
• Support text document processing using local LLMs.
• Develop localized prompts to improve retrieval accuracy.
• Implement chat history, document indexing, and auto re-indexing after file changes.
• Set up MCP integration for OpenText CS, RAG, and enterprise workflows.
• Maintain APIs, backend services, vector DBs, ingestion pipelines, and system integrations.
• Monitor search quality, performance, security, and AI response accuracy.
• Troubleshoot and continuously optimize the AI knowledge platform.
• Attend on-site sessions for system setup, integration, testing, troubleshooting, and project discussions when required.

Employment Arrangement

• Employment type: Part-time
• Work arrangement: Primarily remote
• On-site requirement: Approximately 2–3 half-day sessions per month
• On-site schedule: To be arranged based on project requirements
• Candidates must be able to travel to the project site when required.

Requirements

• Diploma or Degree in Computer Science, Software Engineering, AI, or a related field.
• Proficiency in at least one programming language: Java, Python, or C#.
• Experience in backend development, REST APIs, and DB integration.
• Practical experience in designing or developing RAG applications.
• Familiarity with embeddings, semantic search, hybrid search, chunking, reranking, and prompt engineering.
• Experience with at least one vector DB, such as pgvector, Milvus, Qdrant, Weaviate, Chroma, or Elasticsearch.
• Knowledge of LLM APIs, local LLM deployment, and AI application integration.
• Experience processing and indexing text-based documents.
• Understanding of document permissions, ACL, authentication, and data security.
• Ability to independently analyse requirements, propose solutions, and complete assigned development tasks.
• Able to attend on-site sessions approximately 2–3 times per month.