What you will do In this role you will build the agentic systems that power Teradata's next generation of AI-driven analytics - intelligent agents that reason over enterprise data, invoke Vantage capabilities as tools, and complete multi-step analytical tasks autonomously.
You will design and implement agent skills and plugins that extend the Teradata agent harness, build evaluation frameworks to measure agent quality, and contribute to the reliability and performance of agent workflows running on Vantage. Your work directly enables customers to move from asking Teradata questions to delegating analytical tasks to AI agents.
Success looks like agents in production that solve real customer problems - with measurable accuracy, latency, and reliability benchmarks that outperform what is possible on Snowflake Cortex or Databricks Genie.
Who you will work with You will join a focused team of AI engineers within Teradata's AI Apps, Analytics, and UX Engineering organization, working on the most technically ambitious part of the Teradata product roadmap. We ship code, not demos.
This role reports to the Senior Manager of AI Engineering and collaborates closely with Staff AI Engineers, the Agent Platform team, and Product Management. You will have access to Teradata's world-class data infrastructure and the opportunity to shape how enterprise agents work at scale.
What makes you a qualified candidate - 3-6 years of software engineering experience with at least 2 years building agentic AI systems in production - not just RAG pipelines or chatbots.
- Hands-on experience implementing agent skills, plugins, or tools that extend an agent harness (Claude Code, OpenCode, Codex, OpenClaw, LangGraph, or equivalent).
- Proficiency in Python; Go experience is a strong advantage.
- Understanding of agent planning loops, tool-calling protocols, function calling APIs (OpenAI, Anthropic, or Google format), and prompt engineering for reliability.
What you will bring - Open-source contributions to agent frameworks or LLM tooling - we value engineers who learn in public.
- Experience evaluating and benchmarking agentic systems: building evals, golden datasets, and automated regression testing for agent behaviors.
- Familiarity with Teradata Vantage, SQL query optimization, or columnar analytics - or with a competing platform (Snowflake, Databricks, BigQuery) at depth.
- Experience with vector databases, embedding models, and hybrid retrieval for agent memory and context management.
- Strong written communication - you can explain a complex agent architecture in a document that a PM and a customer engineer can both understand.
- A passion for how AI can unlock potential to help our teams, our customers, and our communities achieve great things.
#LI-CP2
