Senior Real-Time State Estimation Engineer

applied; Sunnyvale (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Applied Intuition, Inc. is powering the future of physical AI. We are building a live HD map estimation layer on our onboard stack to fuse priors with live perception across vehicle programs. You will own the onboard live-map estimator end to end and set interfaces rather than tweak existing systems.

This role emphasizes architecture ownership and close interaction with users to collect feedback, with safety-critical reliability and embedded real-time performance at its core.

Qualifications

• 5+ years building production software.
• State estimation fundamentals in production: factor graphs, filtering, uncertainty propagation.
• Experience fusing heterogeneous sources into a single world estimate with rigorous error characterization.
• Strong modern C++ and ability to meet real-time budgets on embedded compute.
• Rigorous evaluation practices: ground-truth/metrics pipelines to hold operating points.
• Judgment about uncertainty and design for graceful degradation.
• Experience defining system interfaces and negotiating contracts with consumer teams.

Responsibilities

• Own the onboard live-map estimator end to end: fuse map priors with live perception into a real-time world estimate.
• Build onboard map change detection: classify boundary shifts, stop-line moves, road closures.
• Define the map trust contracts the planner uses: confidence semantics and degraded-mode behavior.
• Build the evaluation backbone, ground-truth and metrics pipelines, and regression testing.
• Ship estimation code in modern C++ that meets real-time budgets on embedded compute.
• Extend loop-offboard: aggregate divergence detections across fleet drive logs into correction pipelines.

Skills

5+ years software

State estimation

Uncertainty handling

System interfaces

Evaluation pipelines

Modern C++

Real-time embedded

Tools

GTSAM

C++

Job description

Applied Intuition, Inc. is powering the future of physical AI. We are building a live HD map estimation layer on our onboard stack to fuse priors with live perception across vehicle programs. You will own the onboard live-map estimator end to end and set interfaces rather than tweak existing systems.

This role emphasizes architecture ownership and close interaction with users to collect feedback, with safety-critical reliability and embedded real-time performance at its core.