The setting
's lets data teams build, transform, govern and validate their data workflows, either in a web browser or with command-line tools.
Generated SQL moves faster than the evidence needed to judge its downstream risk.
Review speed protects delivery flow, while lineage, tests, and contracts protect governed transformations.
Who you’d be doing this for
“I spent an hour tracing one tiny edit because the diff didn’t show what it could break.”
Fadi Bahrami · Analytics Engineer · a character in this brief
Maintains production dbt models for a regulated enterprise and reviews AI-assisted project changes.
What is at stake
Generated dbt changes can pass a quick diff review while missing a downstream contract or lineage dependency. You must weigh faster review flow against the evidence reviewers need to trust a promotion.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- review speed vs downstream evidence
- model ranking vs reviewer judgment
- tenant isolation vs useful context
- shared infrastructure vs specialized prediction
Why Fivetran
dbt projects already hold the tests, contracts, lineage, and run history needed to make AI-assisted changes more reviewable.
Written with these in mind
Not your kind of problem? 54 more at Fivetran, or browse every organization.
Where the organization context comes fromThe postings this brief was written from, and the reporting read before it.
The organization context comes from public information. The situation and characters are written for the brief.
Job postings it was written from
Public descriptions of the work at Fivetran. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Staff R&D Software Engineer, Fivetran AI · no longer posted
- 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.
- Sr. Principal AI Systems Architect (opens in a new tab)
- Partner with product, engineering, and analyst-domain experts to translate real analytical workflows into robust AI-assisted product capabilities.
- This role owns the architecture behind the analyst AI system, including metadata contracts, tool interfaces, context assembly, prompt and skill orchestration, evaluation loops, and the operational patterns that make agents useful in real workflows instead of isolated demos.
- Senior R&D Software Engineer, Fivetran AI · no longer posted
- Write and maintain tests, and do hands-on QA to catch issues before customers do
- Considered a trusted expert in your subject area, capable of executing complex, ambiguous tasks with minimal hand-holding
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.
Where similar work appears
Other live briefs connected to this one, and what connects them.
Similar problems at other organizations
Like this one, each of these is about an irreversible change forced by a fixed date.
Schema-change requests are waiting for manual investigation, leaving downstream data exposed to avoidable mistakes.
You have to decide at what point in the Airflow and DataHub evidence trail the AI stops classifying a change and an engineer starts deciding whether to block or accept it.
A quality alert is reaching engineers after a dashboard or ML input has already used the affected run.
You have to decide where the system's work on a failed landing check stops and an engineer's call to hold the run begins.
A request definition can change while the pipeline stays green, leaving downstream systems to read homeowner intent incorrectly.
You have to decide where the watch loop's flagging of affected rows and runs ends and where a data engineer's judgment on holding a run begins.
The same setting, from another role
Each is set around Fivetran’s dbt platform, written for a different role. They’re separate briefs, not the same scenario.
Enterprise CSMs must reconcile conflicting records in 17 of 40 onboarding questions.
You decide whether AI may infer a remaining step from conflicting notes, or must leave that part of the reply for the CSM.
Six of eight Enterprise customers depend on one person to maintain their dbt models.
You need to weigh proof of independent maintenance against the practice time customers will actually protect.
An enterprise customer may remove two business units from its annual renewal today.
You must weigh preserving ten reporting workloads against committing to savings that a full monthly close has not tested.
Other problems with a similar purpose
In each of these, as in this one, the aim is to build machine-learning systems that earn trust by staying explainable where their errors carry real consequences.
An audit found sensitive fields in 7% of shared artifacts that manual review missed, and the classifiers disagree on the edge cases.
You have to build evidence for a production commitment you cannot easily reverse.
One threshold sends very different numbers of drivers into coaching in each region, and reviewers there agree less often.
You have to balance fair treatment of drivers against enough coverage to improve coaching.
Confirmed takeover messages are reaching guests, while legitimate pre-check-in threads are also being blocked.
You must weigh fraud prevention against a guest losing the instructions needed to enter a booked stay.
