We are hiring a hands-on AI Data Platform Engineer to work on a strategic initiative focused on GenAI, knowledge graphs, and enterprise data platforms within a regulated banking environment.
This role involves building knowledge bases, semantic layers, and AI-powered data access systems (RAG, GraphRAG, LLMOps).
Por favor, asegúrese de leer atentamente los siguientes detalles antes de enviar cualquier solicitud.
Key Responsibilities
• Build and manage knowledge base pipelines (structured & unstructured data)
• Develop RAG / semantic search / AI retrieval systems
• Work with graph databases and vector databases
• Design and build APIs (FastAPI or similar) for data access
• Integrate enterprise data sources (S3, SharePoint, data lakes, etc.)
• Implement LLM-based solutions (AWS Bedrock or similar)
• Ensure scalability, performance, and production readiness
Must-Have Skills
• Strong Python + SQL
• Experience with GenAI / LLMOps / RAG pipelines
• Hands-on with PostgreSQL
• Experience with Graph Databases (Neo4j / Neptune / similar)
• API development using FastAPI / REST xohynlm
• Cloud experience (AWS preferred)
• Experience with Docker, CI/CD, Git
Good to Have
• AWS Bedrock / LLM integration
• Frameworks like LangChain, LlamaIndex
• Experience with vector databases / semantic search
• Exposure to Databricks / Kafka / Spark
• Knowledge of GraphRAG / hybrid retrieval systems