About the Role
Fivetran and dbt are building the open data infrastructure that powers AI agents you can trust.
Fivetran is looking for a Staff R&D Software Engineer to join our fast-growing Fivetran AI team. Your data stack was built for humans — but agents are the new primary data consumers, and they have fundamentally different requirements. Agents can’t intuit context; it must be explicitly codified, governed, and traceable. We’re building the governed context layer that solves this problem: Agents Schema, an open standard for storing agent-ready context directly in the customer’s own data warehouse, and Context Builder, the managed service that keeps it filled and fresh.
This role goes well beyond standard engineering. You’ll research emerging techniques in the fast-moving AI landscape and bring real product and market understanding to decide which ideas are worth pursuing — and then you’ll take what you’ve learned and ship it as production software. We’re looking for a true generalist who is willing and able to wear whatever hat the moment calls for: prototyping a new retrieval technique one week, hardening a backend service the next, then doing SRE or QA work when the team needs it. At this level, you’re expected to be a trusted expert beyond your own team — defining technical direction that other teams build on, taking high-level direction and turning it into concrete plans with a high degree of independence, and using sound judgment to decide what deserves your attention. Fivetran AI operates like a startup within Fivetran, and we need engineers who thrive on that range and ambiguity rather than staying in one lane.
Responsibilities
- Research emerging techniques in retrieval, reasoning, and agentic AI, and decide what’s actually worth pursuing for Fivetran AI’s roadmap — then convince others
- Prototype new ideas quickly, then take the ones that prove out and turn them into shipped, production-grade features
- Define technical direction that spans multiple teams within Fivetran AI, ensuring architecture decisions made in one area don’t create problems in another
- Build and maintain both back-end and front-end systems for the Fivetran AI product — from Agents Schema pipelines to the Context Catalog UI
- Drive the AISQL capability forward: natural language to SQL grounded in dbt metric definitions, executed natively against the warehouse
- Take ownership of production reliability across the platform: on-call rotation, incident response, and SRE work to keep the system trustworthy at scale
- Set the bar for testing and QA practices, and do hands-on QA work yourself when it matters most
- Use coding agents to automate the repetitive parts of the job, freeing up time for the research and design work that needs a human
Requirements
- Experience with Python, Java, SQL, dbt, LLMs (Claude, ChatGPT, Gemini), vector databases, BigQuery / Snowflake / Databricks, MCP protocol, React, TypeScript, Kubernetes
- Proven ability to research and implement emerging AI techniques
- Strong product and market understanding
- Ability to work independently and define technical direction
- Experience with backend and frontend development
Conditions
- Full-time hybrid position based out of our Austin, TX office
- Hybrid work model offers a blend of remote flexibility and in-person collaboration, including two days in the office each week