SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Applied Intuition is a $15B-valued AI company powering autonomous systems across automotive, defense, trucking, construction, mining, and agriculture. The Localization, Calibration, and Mapping team delivers high-integrity solutions for real-time navigation in safety-critical environments.
You will own the live map layer on Applied's onboard autonomy stack—a real-time fused estimate of the world built from HD map priors and live perception. This is early-stage work with no incumbent design, giving you the opportunity to set architecture and define interfaces rather than optimize within an existing system.
Key responsibilities:
- Own the onboard live-map estimator end-to-end: fuse HD map priors with live perception into a single, real-time estimate the rest of the stack can trust
- Build onboard map change detection: classify boundary shifts, stop-line moves, road closures from map-perception divergence, and define when the planner should stop trusting the map
- Define map trust contracts for the planner: confidence semantics, degraded-mode behavior, and operating points across vehicle programs
- Build evaluation backbone, ground-truth and metrics pipelines, operating points, and regression testing to prevent quality drift
- Ship estimation code in modern C++ meeting real-time budgets on embedded compute
- Extend the loop offboard over time: aggregate divergence detections across fleet drive logs into map freshness and correction pipelines
The company expects full-time employees to work in-office 5 days per week from the Sunnyvale headquarters, with flexibility for occasional remote work and schedule adjustments.
REQUIREMENTS:
- 5+ years building production software, including at least one shipped system where you owned the estimation core
- State estimation fundamentals proven in production: factor graphs and/or filtering, data association, uncertainty representation and propagation, 3D geometry and transforms
- Experience fusing heterogeneous sources (prior map data, perception output, raw sensors) into a single world estimate with rigorous error characterization
- Strong modern C++ and ability to make estimation code meet real-time budgets on embedded compute
- Rigorous evaluation practice: built ground-truth or metrics pipelines and used them to hold a shipped operating point and prevent regressions
- Judgment about uncertainty: understands graceful degradation vs. catastrophic failure, designs systems accordingly
- Experience defining a system and its interfaces and negotiating those contracts with consumer teams
NICE TO HAVE:
- Map change detection or live/lifelong mapping experience
- HD map semantics: lane graphs, topology, map formats and failure modes
- GTSAM or comparable factor-graph frameworks; Lie group methods
- Degraded-mode or integrity-monitor design for safety-relevant functions
- MS/PhD with focus on state estimation or SLAM
