Our company

At Teradata, we believe that people thrive when empowered with better information. Teradata Autonomous Knowledge Platform activates enterprise intelligence by unifying data, knowledge and business context to achieve tangible outcomes. With Teradata, organizations can provide agents with full context for impact when it matters. Our solution lets businesses connect and scale on premises, in the cloud, or through a hybrid approach. Teradata delivers real business value with AI.

What you'll do

In this role you will design and build the core components of Teradata's agent harness — the runtime environment that enables AI agents to plan, execute, and iterate on complex analytical tasks against Teradata Cloud data at enterprise scale. 

You will be hands-on in Go and Python, implementing the agent execution engine, tool-calling interfaces, agent skill/plugin registries, and the observability layer that makes Teradata's agents trustworthy and debuggable in production. Your work will define how agents interact with Teradata Cloud's query engine, data catalog, and governance layer. 

Success means shipping an agent harness that internal Teradata product teams, ISV partners, and enterprise customers use daily — one that is fast, extensible, and demonstrably superior to alternatives built on Snowflake Cortex or Databricks Genie. 

Who you'll work with 

You will be a senior technical contributor in Teradata's AI Apps, Analytics, and UX Engineering organization, embedded in the team building the Agentic AI Platform. We are a small, high-conviction team that ships — we value code reviews over design docs, and working software over polished presentations. 

This role reports to the Senior Manager of AI Engineering and works directly with Staff and Senior AI Engineers, the PM for Agentic AI Platform, and Teradata's Distinguished Engineers. You will have meaningful influence over technical direction and the freedom to contribute to open-source projects that advance the broader agent ecosystem. 

What makes you a qualified candidate

• Production-level proficiency in Go (required) and Python — you have shipped Go services in a high-throughput, latency-sensitive environment. 
• Hands-on experience building agent harness components: tool-calling runtimes, agent orchestration loops, skill/plugin frameworks, or LLM inference pipelines. 
• Deep understanding of at least one modern agent harness — Claude Code, OpenCode, Codex, OpenClaw, or equivalent — including its architecture, limitations, and extension points. 
• Demonstrated ability to work across the stack: from LLM prompt engineering and function calling to distributed system design and observability. 

What you'll bring

• Open-source contributions to agent harness projects (OpenCode, OpenClaw, LangGraph, or similar) — we will look at your GitHub. 
• Experience integrating AI agents with SQL query engines, data catalogs, or columnar data stores (Teradata Cloud, Snowflake, Databricks, or BigQuery). 
• Familiarity with agent memory architectures: short-term context management, long-term retrieval (vector DBs, hybrid search), and session persistence. 
• Experience with enterprise-grade concerns: RBAC, audit logging, rate limiting, and cost attribution for LLM workloads. 
• Strong opinions about what makes an agent harness good — and the code to prove it. 
• A passion for how AI can unlock potential to help our teams, our customers, and our communities achieve great things. 

#LI-CP2