AI Full-Stack Engineer – LLM / GenAI

Key Responsibilities 1. AI and LLM Development: Integrate OpenAI APIs or other suitable LLM providers into the application. Develop conversational AI capabilities for database troubleshooting and performance analysis. Implement RAG pipelines that retrieve relevant information from DBA runbooks, operational documentation, and historical incidents. Use LangChain, LlamaIndex, or lightweight alternatives where appropriate. Build structured prompts and tool-calling workflows that produce evidence-based recommendations. Implement response validation, source citations, and safeguards against unsupported AI-generated recommendations. 2. Backend Development Develop backend services and REST APIs using Python and FastAPI. Implement APIs for database inventory, health checks, metrics, incidents, logs, and AI-assisted troubleshooting. Integrate database connectivity libraries and monitoring APIs. Implement authentication, role-based authorization, input validation, error handling, and audit logging. Design modular services that support additional database platforms without major architectural changes. 3. RAG and Knowledge Management: Implement a knowledge ingestion pipeline for technical documents, runbooks, troubleshooting guides, and operational procedures. Use PostgreSQL and pgvector for document metadata, embeddings, and semantic search. Develop document chunking, embedding generation, retrieval, and context assembly. Ensure AI responses can reference the source documents supporting their recommendations. 4. Database Monitoring and Integration: Integrate AWS CloudWatch for Amazon RDS and related AWS monitoring data. Develop PostgreSQL monitoring integrations for active sessions, locks, expensive queries, database size, and other operational metrics. Design a monitoring integration framework that can later support Prometheus and Grafana. Collaborate with the DBA/Database SME to validate monitoring queries, operational recommendations, and database-specific behavior. 5. Frontend and User Interface: Develop a responsive, modern web interface using React and TypeScript, or an equivalent framework. Build dashboard components for database health, CPU and memory utilization, storage, incidents, performance issues, and recent activity. Implement an AI chat interface for natural-language questions and troubleshooting workflows. Provide views for query analysis, recommended remediation, runbooks, and incident summaries. Connect frontend components to FastAPI endpoints. Containerize the application using Docker and Docker Compose. Create development and test environments with clear setup instructions. Implement automated tests for APIs, RAG retrieval, AI response quality, and database integrations. Develop logging, health checks, and basic application observability. Document deployment, configuration, troubleshooting, and maintenance procedures. Required Technical Skills Strong Python development skills. Experience building REST APIs with FastAPI or a comparable Python framework. Practical experience integrating LLM APIs, particularly OpenAI or equivalent providers. Understanding of RAG, embeddings, vector search, and prompt engineering. Experience with PostgreSQL and SQL; familiarity with pgvector is preferred. Experience with React, TypeScript, or another modern frontend framework. Experience with REST APIs, JSON, authentication, and secure application development. Familiarity with Docker and containerized application deployment. Experience with Git, automated testing, and maintainable software architecture. Preferred Qualifications Experience with LangChain, LlamaIndex, or comparable LLM orchestration frameworks. Experience with AWS, CloudWatch, Amazon RDS, and IAM. Familiarity with Prometheus, Grafana, and metrics-based monitoring. Experience with MCP servers, tool calling, or agentic AI workflows. Understanding of SQL execution plans, database performance metrics, locks, connections, and query optimization. Experience building AI assistants for infrastructure, operations, observability, or enterprise support. Familiarity with Oracle, PostgreSQL, Cassandra, or Microsoft SQL Server is a plus, but not required. Collaboration Model The engineer will work directly with the DBA/Database SME, who will provide: Database architecture and technical requirements. Approved monitoring queries and diagnostic procedures. Troubleshooting use cases and operational runbooks. Database-specific validation and acceptance criteria. Guidance on safe remediation and production controls. The engineer is expected to translate these requirements into working software and communicate implementation decisions, blockers, and progress clearly. Engagement Expectations We are looking for a pragmatic engineer who can make sound architectural decisions, prioritize essential functionality, reuse established libraries, and avoid unnecessary infrastructure or framework complexity. The initial focus is a functional, demonstrable MVP rather than a full enterprise platform. Multi-database support, advanced autonomous agents, and automated remediation will be considered in later phases. To apply: Please provide a resume or portfolio highlighting relevant LLM applications, RAG implementations, Python APIs, frontend development, and deployment experience. Include examples of projects you personally implemented and your availability for a contract or part-time engagement.