Key skills
Retrieval-Augmented Generation (RAG) architecturesEmbedding modelsRetrieval optimizationSnowflake Cortex AgentsSnowflake Cortex AnalystsSnowflake Cortex SearchSnowflake Cortex vector functionsPythonSQLData pipeline developmentVector databasesIndexing strategiesUnstructured data processingDocument intelligence workflowsLLM orchestration tools LangChainLLM orchestration tools LlamaIndexLLM orchestration tools GuardrailsTesting frameworks for AI systemsObservability frameworks for AI systemsReliability frameworks for AI systemsGuardrail frameworks for AI systemsSystem designAIMLLLMRAGLangChainLlamaIndexAnalyticsSnowflakeCommunication
About this role
Cognizant is seeking a highly technical, hands-on Senior Data Engineer to architect, build, and scale chat-with-data capabilities for an enterprise-grade, customer-facing platform. The ideal candidate will have experience with Retrieval-Augmented Generation (RAG) systems and Snowflake Cortex, focusing on building scalable AI-driven capabilities.
Responsibilities:
- Develop and scale RAG-based workflows powering chat-with-data and conversational analytics experiences
- Build and operationalize Snowflake Cortex Agents, Analysts, and Search solutions
- Design ingestion, preprocessing, embedding, and vector search pipelines supporting large-scale datasets
- Implement guardrails, evaluation metrics, and automated testing frameworks for trustworthy AI
- Optimize performance across embedding models, vector indexes, and LLM inference layers
- Ensure secure handling, governance, and monitoring of structured and unstructured data assets
- Collaborate with cross-functional engineering, ML, and product teams to deliver scalable AI-driven capabilities
- Drive continuous improvement in retrieval quality, latency, observability, and failure handling
Requirements:
- Hands-on expertise with RAG architectures, embedding models, chunking, and retrieval optimization
- Strong experience with Snowflake Cortex (Agents, Analysts, Search, vector functions)
- Proficiency in Python and SQL with experience building scalable data pipelines
- Solid knowledge of vector databases and indexing strategies
- Experience with unstructured data processing and document intelligence workflows
- Familiarity with LLM orchestration tools (e.g., LangChain, LlamaIndex, Guardrails)
- Experience building testing, observability, reliability, and guardrail frameworks for AI systems
- Strong system design, communication, and problem-solving skills