Senior Analyst - Data Engineering

As a Senior Analyst - Data Engineering, you will be responsible for designing and maintaining reliable, scalable, and secure LLM orchestration services using Python. Your primary focus will be on developing RAG pipelines, establishing CI/CD practices, ensuring observability, and adhering to code quality standards. **Key Responsibilities:** - Design and implement complete RAG pipelines including embeddings generation, vector search, prompt injection, LLM invocation, and post-processing. - Build modular, maintainable code with clear interfaces for context assembly, retrieval logic, prompt construction, LLM invocation, and data persistence. - Optimize pipeline performance through token caching strategies, async I/O patterns, intelligent caching, and resource right-sizing. - Implement best practices for LLM orchestration ensuring efficient token usage and response quality. - Design and implement automated CI/CD pipelines with comprehensive test coverage, security scanning, and gated deployments. - Manage deployment strategies across dev, staging, and production environments. - Establish branching models, pull request workflows, code review standards, and merge strategies with quality gates. - Implement comprehensive logging, tracing, and metrics collection for RAG pipelines. - Track key performance indicators including RAG cache hit rates, retrieval latency, LLM response times, and error rates. - Set up alerting mechanisms and monitoring dashboards using Azure Application Insights or similar tools. - Maintain high code quality standards with well-organized project structures, proper error handling, retry logic, and comprehensive logging. - Write unit tests, integration tests, and end-to-end tests with appropriate mocking strategies. - Implement database best practices including stored procedures, proper table design (primary keys, audit fields, indexing). - Create and maintain thorough technical documentation. - Enforce security gates throughout the development lifecycle. **Qualifications Required:** - Real-world experience with Azure Functions or similar serverless frameworks. - Experience with Azure SQL or similar relational databases. - Strong understanding of testing methodologies: unit testing, integration testing, and end-to-end testing with mocking frameworks. - Experience with CI/CD pipelines using Azure DevOps or GitHub Actions. - Knowledge of container builds, scanning, and deployment workflows. - Familiarity with Git branching strategies, PR workflows, and merge strategies. - Hands-on experience with LLM orchestration and RAG architectures, including embeddings, vector search, and prompt engineering (Good to have). - Experience with LLM orchestration frameworks such as llama_index, LangChain, or similar (Good to have). - Proficiency with Azure AI Search, Azure OpenAI. - Strong grasp of modular design, clean code principles, and API design. - Experience with error handling, retry mechanisms, and resilience patterns. - Understanding of asynchronous programming and performance optimization.,