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.
F10 evaluation needs comparable missions, while early aircraft configurations are still changing.
Deep Learning needs enough usable mission coverage to judge perception performance, while manufacturing records must preserve which configuration produced each mission.
Who you’d be doing this for
“My field leads keep asking what changed between flights, and I need an answer before we plan around these missions.”
Taewoo Zhou · Utility Operations Manager · a character in this brief
Oversees inspection missions that depend on confidence that longer-range aircraft behave predictably in changing field conditions.
What is at stake
F10 evaluation missions cannot yet be compared reliably across aircraft configurations. You must decide which mission, configuration, and model signals belong in the first reusable dataset.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- early F10 coverage vs consistent configuration history
- model-specific speed vs reusable data contracts
- media discoverability vs governed access
- manufacturing fidelity vs simple evaluation slices
Why Skydio
F10 missions connect longer-range aircraft behavior to the autonomy data flywheel that supports future 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.
- Senior Operations Systems Engineer (opens in a new tab)
- This implementation will build on the foundation of our existing systems including NetSuite, Arena, Jira, and our home-grown MES.
- Help integrate new data sources while maintaining the Palantir ontology
- Wireless Hardware Engineer Intern - Summer 2027 (opens in a new tab)
- Self-driven, detail-oriented, and eager to learn and contribute in a fast-paced setting.
- You will work closely with RF and antenna engineers to improve how wireless performance data is collected, processed, and visualized.
- Senior Autonomy Engineer, Data Curation (opens in a new tab)
- Close peers will include the Deep Learning and Computer Vision teams.
- Build and operate pipelines that transform raw autonomy logs & media into curated datasets with strong observability and clear ownership to make curated data more broadly reusable.
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 make operational data dependable at the exact moment someone needs to act on it.
Late partner records leave valid quote journeys out of the next morning’s funnel view.
You have to weigh faster completeness against duplicate policy-start reporting.
Duplicate TMS cases must fall below 1% of late-shipment events within ten business days.
You must weigh fast exception escalation against the confidence operators need in every case.
Launch operators cannot explain why nearby homes receive different availability answers.
You must weigh a fast review flow against preserving the flight constraints behind every route.
