Data Platform Engineer (Ai-Enabled)

Drive the creation of a scalable and high-quality data intensive platform leveraging some of the latest methodologies such as Data Virtualization and Data Domains

• 5+ years overall experience in Big Data or Enterprise large-scale application development using scalable tools like Databricks, Scala, Java, and the Python ecosystem.
• Deep understanding of data modeling, data warehousing concepts, methodologies, and best practices.
• Strong experience with data processing (e.g., Spark, Starburst, Snowflake, Redshift), storage (e.g., Hadoop, MongoDB, Oracle), and ETL (e.g., Airflow, Ab Initio, Talend) solutions.
• Experience with data engineering techniques such as building data lakes and data warehouses, data mesh architectures, data pipelines, and ETL vs. ELT patterns.
• Strong expertise in Starburst/Trino with deep understanding of data federation and data virtualization architectures.
• Experience with real-time data processing and data virtualization technologies such as Starburst, Snowflake, and Flink (preferred).
• Experience with designing and developing distributed systems, handling structured and unstructured data to store, analyze, and report.
• Experience with developing and maintaining large and complex database systems using relational databases like Oracle, and other big data technologies like Hadoop, Spark, etc.
• Proficient in PL/SQL and Unix Shell scripts. Strong SQL, PL/SQL development, and database tuning experience.
• Experience in designing Online Transaction Processing (OLTP), Operational Data Store (ODS), and Data Warehouse applications.
• Experience with Data Quality and data lineage.
• Demonstrable experience with AI Agents, including their design, development, and integration into data engineering workflows and software systems.
• Practical knowledge of Model Context Protocol (MCP) servers, including: Setting up and configuring MCP servers to expose data tools, database connections, and APIs as contextual resources for LLM-powered agents.
• Designing MCP-compatible tool interfaces that allow agents to query, transform, and validate data autonomously.
• Understanding MCP's client-server architecture and its role in enabling secure, standardized communication between AI agents and enterprise data systems.
• Understanding of Retrieval-Augmented Generation (RAG) principles, including vector databases (e.g., Pinecone, Weaviate, ChromaDB) and advanced retrieval techniques for grounding agents in enterprise data.
• Awareness of Large Language Models (LLMs) (e.g., OpenAI, Gemini, Claude, Llama) and their practical application in data engineering contexts such as automated schema inference, natural language querying, and intelligent data cataloging.
• Bachelor’s degree/University degree or equivalent experience