Summary
✨ AI‑Generated
An opportunity for an innovative engineer to develop perception systems for autonomous technologies. The role involves research, deep technical exploration, and building AI models for complex real-world environments.
Highlights
Advanced AI engineering role focused on autonomy, spatial intelligence, and solving challenging problems at the intersection of robotics and machine learning.
Description
Our work
We are a well capitalized stealth VC-backed startup building a new type of spatial AI capable of universally solving autonomy.
We innovate at the foundational layer of AI by training our own AI models.
Our team
Our team is composed of AI pioneers and leaders from Google X, Google Brain, and Space Agencies.
Several of us are repeat founders, with deep commercialization insights across multiple enterprise segments.
We enjoy long, deep ideations around entirely unexplored AI use cases in autonomy (cars, drones, robots).
Who you are
Curious: you have an innate curiosity for all things intellectual, and it’s something you can’t turn off.
You obsess over finer details others miss.High intensity: you thrive in a high-stakes environment, and are driven by an innate obsession, not by others.Fast learner: you gravitate toward learning new things, and often find yourself learning more quickly than everyone around you.Driven by discomfort: you enjoy leaving your comfort zone and challenging yourselfCreative: track record of solving hard problems with solutions worthy of academic papersEducator: you take pride in your ability to communicate complex topics clearly and have excellent speaking and writing skills.Zero ego: you don’t just take feedback, but truly see it as a gift.
You don’t wait until feedback is given, but solicit it with every opportunity.Founder mentality: you roll up your sleeves to help solve the most pressing problem on a given day, even if it has nothing to do with this job post.
Where you are
San Francisco, CA
Technical Skills
State Estimation: Real depth in visual-inertial odometry and SLAM.
Factor graphs or filtering, IMU preintegration, observability, loop closure.Degraded Conditions: Low texture, high glare, repetitive or moving scene content.
You have shipped something that held up when the scene stopped cooperating.Uncertainty: Calibrated confidence, so the system reports that it is lost before the pose error grows rather than after.
Conformal or selective prediction a plus.Calibration: Intrinsics, extrinsics and time synchronisation across cameras, IMU and GNSS on real hardware, not a dataset.Programming: Strong C++, comfortable in Python.
Eigen, GTSAM, Ceres or equivalents.ML: You have an opinion about when a learned component helps and when it hides the problem, and you can defend either side.Deployment: Jetson-class embedded targets a plus.Domain-Specific: Maritime, aerial or any low-feature environment.
