Senior AI Data Engineer

Our Company

At Teradata, we believe that people thrive when empowered with better information. That’s why we built the most complete cloud analytics and data platform for AI. By delivering harmonized data, trusted AI, and faster innovation, we uplift and empower our customers—and our customers’ customers—to make better, more confident decisions. The world’s top companies across every major industry trust Teradata to improve business performance, enrich customer experiences, and fully integrate data across the enterprise.

As the recognized leader in data and analytics, Teradata is all about empowering high-impact business outcomes to unleash the potential of great companies. We focus every day on helping customers build lasting analytic capabilities and drive differentiated value through our flexible delivery of analytics at scale on an agile data foundation, now enhanced with cutting-edge AI, Generative AI, and Agentic AI capabilities.

Our mission is to build the world-class AI and data ecosystem for the industry leader in mega-scale Analytics platforms. Teradata is looking for senior engineers who can bridge the gap between data infrastructure and artificial intelligence. We need innovators who can architect robust data pipelines while building intelligent systems including autonomous AI agents, multi-agent systems, and AI-powered applications that can reason, plan, and take actions to solve complex business problems.

Role Overview

The Senior AI Data Engineer will architect and build both the data infrastructure and intelligent AI systems that power enterprise analytics, with primary focus on:

Data Engineering and Architecture

Design and build scalable data pipelines for batch and real-time processing using Teradata Vantage and enterprise data platforms. Develop integration solutions acquiring data from multiple sources, transforming it into analytics-ready formats optimized for AI/ML workloads. Leverage Teradata's advanced SQL, in-database analytics, and parallel processing. Create feature engineering pipelines and feature stores for ML operations. Implement data versioning and lineage tracking.

Agentic AI and Multi-Agent Systems

Design autonomous AI agents that perceive, reason, plan, and execute complex tasks with minimal human intervention. Develop agentic workflows using LangChain, LangGraph, n8n, and orchestration tools. Build multi-agent systems where specialized agents collaborate through orchestration frameworks, task decomposition, and communication protocols. Create workflow automation with visual and code-based builders. Implement feedback loops, self-improvement mechanisms, and human-in-the-loop supervision. Deploy Model Context Protocol (MCP) for agent-to-agent and agent-to-system communication.

 AI-Powered Data Applications

Build applications integrating LLMs, generative AI, and agentic capabilities with enterprise data systems. Design natural language interfaces for data operations, querying, and analytics. Create AI copilots that understand context, query databases, generate reports, and execute multi-step workflows. Develop tool-using agents that interact with APIs, databases, and external systems. Implement AI-driven automation for analysis, insight generation, and decision support.

 LLM Integration and RAG Systems

Architect LLM solutions using foundation models and fine-tuned variants. Apply prompt engineering, few-shot learning, and chain-of-thought reasoning. Build retrieval-augmented generation (RAG) systems connecting LLMs with enterprise data using vector databases. Design hybrid search combining semantic and keyword approaches. Develop data ingestion for vector databases including chunking, embedding generation, and metadata management. Optimize inference with caching strategies.

 Data Management and Governance

Implement data management including lineage tracking, metadata management, quality monitoring, and cataloging. Build governance frameworks ensuring privacy, security, and compliance. Design data models for analytical and operational workloads. Create access controls and audit logging for AI applications.

 System Architecture and Infrastructure

Design production-grade architectures integrating data platforms with AI systems. Build event-driven architectures for data processing and AI workflows. Implement state management for conversational AI and long-running agents. Create comprehensive observability, monitoring, and logging infrastructure. Deploy using containerization and orchestration technologies.

Key Responsibilities

• Architect scalable data pipelines for batch and real-time processing supporting AI/ML workloads and low-latency inference
• Design and implement autonomous AI agents and multi-agent systems for enterprise data operations
• Build production-grade AI applications integrating LLMs, GenAI, and RAG systems with vector databases and enterprise data warehouses
• Develop feature engineering pipelines and feature stores for ML model training and inference
• Create AI copilots and assistants using advanced prompt engineering and agentic workflows for data querying, analysis, and insight generation
• Design event-driven architectures integrating data processing with AI agent coordination
• Implement comprehensive observability, data quality frameworks, and monitoring across data pipelines and AI systems
• Build data governance solutions including security controls, AI safety measures, and compliance frameworks for production systems
• Collaborate with data scientists, analysts, and product teams to define requirements and success metrics
• Provide technical leadership on architecture decisions and stay current with emerging technologies in data engineering and AI domains

Required Qualifications

• 5+ years of data engineering experience building production data pipelines and ETL/ELT solutions
• 3+ years building and deploying production AI applications, LLMs, and GenAI systems
• Strong proficiency in Python and SQL for data processing, analytics, and AI development
• Hands-on experience with LLMs, GenAI, prompt engineering, RAG systems, and agentic workflows using frameworks such as LangChain, LangGraph, or n8n
• Experience with vector databases, semantic search, and data processing technologies including parallel processing frameworks
• Strong understanding of relational databases, data warehouses, and data modeling; knowledge of Teradata Vantage platform preferred
• Solid software engineering fundamentals including API design, microservices, and distributed system architecture
• Experience with cloud platforms (AWS, Azure, or GCP) for data and AI workloads
• Understanding of data governance, security, and compliance best practices
• Excellent problem-solving skills with ability to architect complex integrated systems
• Strong communication and collaboration skills for cross-functional leadership
• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or related field (or equivalent experience)
•  

Preferred Qualifications

• Experience with Teradata platform including Vantage, QueryGrid, VantageCloud, and AI/ML capabilities
• Hands-on experience building multi-agent systems, agent orchestration frameworks, and agentic workflows using LangChain, LangGraph, n8n, or similar platforms
• Knowledge of agent reasoning patterns, Model Context Protocol (MCP), and multi-step task execution strategies
• Experience with advanced RAG techniques including hybrid search, query rewriting, re-ranking, and multiple vector database technologies
• Knowledge of data lakehouse architectures, modern data platform patterns, and streaming technologies for real-time processing
• Experience with data orchestration tools, workflow management systems, and feature store implementations for ML operations
• Experience with containerization (Docker), orchestration (Kubernetes), and distributed systems for data and AI workloads
• Knowledge of LLM evaluation frameworks and observability platforms for both data pipelines and AI systems
• Experience with diverse data storage patterns including SQL, NoSQL, and graph databases for knowledge graphs
• Knowledge of data versioning, lineage tracking, metadata management, and data quality frameworks
• Understanding of AI ethics, responsible AI practices, and data privacy regulations
• Contributions to open-source projects in data engineering or AI domains

#LI-NM1