- Salary
- $200k – $300k/yr
- Location
- San Francisco, California, US
- Workplace
- Remote
- Type
- Full-time
- Department
- Engineering
- Seniority
- Lead
- Experience
- 3+ years
- Source
- Y Combinator
Description
In a Nutshell
We are looking for exceptional localization engineers to help us replace GPS by spring 2027. Your work will ship every week to drones operating in active combat.
About Theseus
Drones need to know where they are, but GPS is a luxury on the modern battlefield. We built Cyclops, our visual localization software, to enable precise, autonomous navigation without GPS.
Just two years in, we have customers across every branch of the U.S. military, major defense primes, and our product is actively used in combat in Ukraine. We expect to sell more than 10,000 licenses this year. Our next challenge: take that capability across ground, air, and maritime environments to build a universal alternative to GPS.
The Role
We are looking for robotics engineers with SLAM, VIO, localization, or state estimation experience. You will work on the estimator itself, meaning the visual-inertial odometry, the map matching, and the sensor fusion that turn camera frames and IMU samples into a position the flight controller can trust. Every day, you will work on feedback beamed in from real deployments across the world, and your changes will ship to devices in the field every single week. We want you to lead much of the localization work we do.
What you will do:
- Work on the visual-inertial odometry, the map matcher, and the filter that fuses them, so that Cyclops holds an accurate position in daylight, at night, over featureless terrain, and on IR cameras.
- Build features that increase availability and reduce operator setup, such as faster initialization, recovery after the estimate has been lost, better handling of poor calibration, and honest uncertainty reporting so the flight controller knows when to trust Cyclops.
- Take problems that arrive as flight logs from customer deployments, reproduce them in replay, form a hypothesis about why the estimate diverged, fix it, and prove the fix across our library of recorded flights before it ships, coordinating with forward deployed engineering so it reaches the customer who reported it.
- Prototype next-generation algorithms aimed at order-of-magnitude gains in accuracy, robustness, and availability, tested against the same flight library as everything else, adopting from the literature what survives contact with real data.
- Ship regularly. New features and fixes ship at a weekly cadence, and we shoot to ship new models within days / weeks.
Who we are looking for:
- 3+ years of experience (Mid level) or 5+ years of experience (Senior) building and deploying state estimation, SLAM, or visual-inertial odometry systems that shipped in a product or were validated in field testing.
- Depth in the estimation fundamentals. You can derive an EKF or a factor graph on a whiteboard, reason about frames and rotations on SO(3) and SE(3), explain what IMU preintegration does and why, and talk about observability, consistency, and what happens to your covariance when a sensor drops out.
- A working grasp of the geometry underneath visual localization: camera models including fisheye and thermal, calibration, epipolar geometry, feature tracking, and bundle adjustment.
- Experience with at least one modern estimation toolchain such as GTSAM, Ceres, or an open VIO stack like OpenVINS, ORB-SLAM, or VINS, and enough understanding of what it does internally to modify it rather than just configure it.
- Production C++ in a Linux environment. Our product runs on ARM edge compute, so you should be comfortable reasoning about latency, memory, and what a change costs on a small processor, even if performance tuning is not your specialty.
- An engineering mindset focused on outcomes. You know the difference between the fix that makes this week's flight logs clean and the redesign that makes next year's product better, and you can tell us which one a given problem needs
Nice to have:
- Experience with camera/IMU calibration
- Map matching, bundle adjustment, or georegistration against aerial or satellite imagery
- Experience with drones, ArduPilot, MAVLink
- Real-time deployment on embedded devices
What else
We are willing to pay up to $300,000 base. The final cash pay for this role will depend on a variety of factors, including a specific candidate's experience, qualifications, skills, working location, and projected impact. The compensation package may additionally include: equity compensation; benefits such as medical, dental and vision insurance; paid time off; and more.
Theseus is an equal opportunity employer and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.