The setting
's lets heavy mining trucks and equipment operate on their own at customer mine sites. It combines vehicle controls, sensors, computers and fleet software.
Comparable shift evidence is pulling against the differences in how each vehicle reports its work.
Mine operators need one view of production while vehicle embodiments preserve distinct state and telemetry behavior.
Who you’d be doing this for
“I spent half the morning matching truck logs to the shift sheet, and the superintendent still asked which number to trust.”
Tsehay Wanjala · Mine Operations Manager · a character in this brief
Runs a mixed-brand surface mine fleet and must justify whether autonomous hauling improves shift production.
What is at stake
Mine managers cannot compare autonomous shifts without rebuilding truck data by hand. You must decide which fleet measures belong in one view without hiding meaningful vehicle differences.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- fleet-wide comparability vs vehicle-specific meaning
- fast operator decisions vs trustworthy shift boundaries
- reusable platform contracts vs site-level fit
- production visibility vs stable live state semantics
Why Applied Intuition
Control Center telemetry and vehicle-platform software already connect autonomous fleet activity to the operational decisions made at mine sites.
Written with these in mind
Not your kind of problem? 93 more at Applied Intuition, 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 Applied Intuition. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Vehicle Controls - Technical Lead (opens in a new tab)
- Characterize the dynamics of customer vehicles across many embodiments — haul trucks, excavators, wheel loaders, dozers, and more — to create tailored controls solutions and close the gap between simulation and real-world behavior
- Build calibration and vehicle characterization workflows that scale controls performance from a single prototype to fleets of vehicles without per-vehicle hand-tuning
- Software Engineer - Control Center (opens in a new tab)
- As a Software Engineer on the Control Center team, you will build the central operational platform that connects autonomous vehicle fleets to human operators across a wide range of industries including mining, commercial trucking, defense, industrial automation, and consumer AVs.
- In this role, you will own core platform domains end-to-end, building low-latency, ultra-reliable backend systems that scale across diverse vehicle types and operational environments-from public cloud deployments to air-gapped, on-premise sites.
- Software Engineer - Onboard Maps (opens in a new tab)
- Build our onboard map change detection: classify situations like boundary shifts, stop-line moves, and road closures from the divergence between map and perception, and define when the planner should stop trusting the map
- Define the map trust contracts the planner builds against: confidence semantics, degraded-mode behavior, and the operating points that hold across vehicle programs
- Software Engineer - C++ (opens in a new tab)
- Whether applying your experience to application-level onboard software in a modern C++ codebase powering on-road products or building systems that operate 200+ ton mining vehicles on deformable off-road terrain, you’ll play a key role in building the autonomy stack powering the next generation of intelligent vehicles.
- Mechatronics Integration Engineer, Vehicle OS (opens in a new tab)
- Build a deep understanding of mining vehicle system architecture and software-hardware interactions, including reverse-engineering third-party systems
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 turns on moving faster inside a system others depend on.
Vehicle-platform teams cannot reliably connect a planned release to one comparable NVIDIA Thor result.
You must weigh faster self-service access against protected hardware capacity and trusted evidence.
Fleet managers are delaying AI-client connections because they cannot test what data each scope exposes.
You must weigh fast operational answers against permissions that remain understandable and reversible.
The same setting, from another role
Each is set around Applied Intuition’s Mining Autonomy and Drive-by-Wire System, written for a different role. They’re separate briefs, not the same scenario.
Older haul trucks wait in the workshop for custom autonomy installations.
You must decide what belongs in a common module and what remains truck-specific.
One haul truck leaves autonomous service when dust reaches its lidar enclosure.
You must choose what gets installed across six trucks before drilling makes the retrofit hard to undo.
One autonomous haul truck loses position on rough loaded routes.
You must weigh a tougher installation against service access and repeatable calibration.
Other problems with a similar purpose
In each of these, as in this one, the aim is to turn fragmented, conflicting operational signals into one clear, actionable call.
Checking customers retry account actions when the mobile app and backend services tell an incomplete story.
You decide where the AI's trace of an incident stops and where the on-call engineer's confirmation of the cause begins.
Conflicting updates are letting carrier-integration risks reach readiness reviews too late.
You must decide which dependency changes the workflow sends straight to a Program Manager as uncertain and which it records as flags for the readiness record.
Regional production can stop while aggregate workspace activity still looks healthy.
You must decide where the ranking stops and the CSM starts: which signals set an account's place in the order, and which the CSM reads for themselves before choosing what to say.
