The setting
makes drones for public safety agencies, government, and businesses. Its use onboard software to fly missions on their own, for work such as inspection, emergency response, and site security.
Simulator failures need speed without turning incomplete context into a release decision.
The triage flow must preserve fast investigation while protecting engineers from confident but unsupported failure classifications.
Who you’d be doing this for
“My control room asks whether the next update changes a mission, and I need a straight answer.”
Aisha Sabbagh · Utility Operations Manager · a character in this brief
Oversees remote inspection missions that depend on fleet software behaving predictably before a dock network is expanded.
What is at stake
Simulator failures keep reaching different owners with different explanations. You must decide whether the system only gathers evidence or also proposes the first routing call.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- triage speed vs simulation capacity
- broad context vs traceable evidence
- known signatures vs novel failures
- consistent routing vs local engineering judgment
Why Skydio
Skydio Simulator evidence informs autonomy changes that reach aircraft and docked fleet operations.
Written with these in mind
Not your kind of problem? 74 more at Skydio, 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 Skydio. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Manufacturing Software Engineer Intern - Winter 2027 (opens in a new tab)
- Develop an AI-powered triage system that can inspect drone hardware and suggest which parts need to be repaired.
- We build all parts of the software stack in-house, including embedded systems, middleware, autonomy, cloud infrastructure, manufacturing infrastructure, and automation.
- Autonomy Engineer Intern, Autonomy Infrastructure, Systems and Tools, 2027 (Zurich) (opens in a new tab)
- Autonomy Engineer Intern, Autonomy Infrastructure, Systems and Tools, 2027 (HQ) (opens in a new tab)
- Senior Software Engineer - Android Platform (opens in a new tab)
- Every feature we build touches real hardware, real airspace, and real missions — and we hold ourselves to the standard that our software must be reliable, performant, and intuitive enough for high-stress, high-stakes operation.
- You'll work at the intersection of Skydio's autonomous flight engine, connected cloud services, and physical controller hardware to build products that give drone operators superpowers.
- Embedded Software Engineer Intern - Winter 2027 (opens in a new tab)
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.
The same setting, from another role
Each is set around Skydio’s Skydio autonomous drones, written for a different role. They’re separate briefs, not the same scenario.
Public-safety proposals conflict on sites and terms, slowing qualified pursuits.
You decide how far a first draft goes when Salesforce and seller notes disagree on a site count or term, before a seller reviews it.
Campus police leaders need event coverage that survives risk and procurement review.
You must decide what the pilot proves now and what it must secure for expansion.
A corrections department must score statewide drone offers in 21 days.
You must set terms that win the award without making every facility carry the same readiness risk.
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.
