PNT Software Engineer

Ulysses Inc. • San Francisco, CA

5d • $180,000 - $260,000

About The Position

Ulysses is hiring a Positioning, Navigation, and Timing (PNT) Software Engineer to develop accurate, reliable localization for autonomous surface and subsea vehicles. The role primarily focuses on inertial navigation, Doppler velocity log (DVL), and GNSS technologies, while contributing to broader positioning, navigation, and acoustic development efforts. The engineer will work closely with electrical, robotics, and mechanical engineering teams across the Mako, Leviathan, and Kraken platforms.

The position covers tightly coupled navigation and state estimation, docking and recovery perception, surface situational awareness, sensor calibration, embedded real-time perception, core optimization and sensor-model libraries, and mission-data logging and validation. The work includes deploying and validating systems on real vehicles and improving reliability using field results.

Requirements

• Has shipped perception or navigation software on autonomous vehicles and can provide examples of its results.
• Experience deploying state estimation on real vehicles in real environments outside labs and simulation; experience may be in air, ground, marine, or space.
• Demonstrated ability to take estimation systems from mathematical foundations through production code to field-validated performance.
• Strong foundations in Kalman filtering, factor graphs and smoothing, nonlinear least-squares optimization, and observability analysis.
• Hands-on inertial navigation experience, including IMU error modeling, preintegration, and tightly coupled fusion with aiding sensors such as GNSS, DVL, or vision.
• Sensor calibration experience, including camera intrinsics, extrinsics, and camera-IMU calibration; factory-floor and online field calibration are desirable within this requirement.
• Proficiency in Rust or C++ for real-time, safety-critical software and Python for prototyping and analysis.
• Experience with optimization and estimation frameworks such as Ceres, GTSAM, or SymForce, or experience developing equivalent tools.
• Comfort working with embedded Linux compute, sensor drivers, time synchronization, and real-time performance on constrained hardware.
• Strong debugging instincts and ability to use logs and replay to trace estimation problems to timestamps, calibration, sensor faults, or math.
• Experience building logging, deterministic replay, and autonomy-software evaluation tools.
• Ability to collaborate across electrical and mechanical engineering on sensor selection, mounting, time synchronization, and hardware constraints.
• Strong problem-solving skills and demonstrated ability to work independently in dynamic environments.

Nice To Haves

• Marine navigation and sensing experience, including DVL, USBL/SBL, INS, multibeam, sidescan, or forward-looking sonar.
• Experience with acoustics and array processing, including hydrophone or microphone arrays, beamforming, or direction-of-arrival estimation.
• Advanced GNSS experience, including RTK, carrier-phase and time-differenced carrier-phase processing, or correction services.
• Experience deploying deep-learning perception on edge hardware using TensorRT, ONNX, or similar, especially in degraded visibility.
• Embedded firmware experience, including microcontrollers, CAN, bootloaders, or low-level sensor interfaces.
• Experience leading or mentoring a perception or navigation team.

Responsibilities

• Architect and implement factor-graph-based, tightly coupled navigation for subsea and surface vehicles, fusing IMU, DVL, pressure, USBL/SBL acoustic positioning, and surfaced GNSS/RTK to bound position error across multi-day dives.
• Contribute to vision and acoustic localization for autonomous Mako docking with Kraken and for Leviathan's safe operation around other vessels.
• Fuse radar, AIS, and EO/IR camera data into a surface track picture that supports collision avoidance and COLREGs-compliant autonomy on Leviathan.
• Own end-to-end IMU, DVL, and GNSS calibration, including factory end-of-line calibration and online calibration that maintains accuracy through shock, thermal cycling, and pressure.
• Help bring up and run perception on embedded Linux, including GPU-accelerated inference, and process multi-camera video, sonar, and hydrophone arrays in real time within tight power budgets.
• Build optimization, factor-graph, and sensor-model libraries used by other teams for estimation, planning, and control.
• Build logging and deterministic mission-data reprocessing so dives can serve as regression tests, and drive reliability improvements based on field results.
• Collaborate with electrical and mechanical teams on sensor selection, mounting, time synchronization, and hardware constraints.
• Debug estimation issues using logs and replay, tracing problems to timestamps, calibration, sensor faults, or mathematical causes.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed