Quidient

Senior Offline Mapping Engineer

Columbia, Maryland, United States · Senior

Sponsorship not specified$175k-$230kDetected 2 days ago

C++Deep LearningPyTorchComputer VisionLLMsRoboticsResearch

About the role

You will enhancethe pipeline that turns real-world captures into highly accurate, production-quality 3D reconstructions.
This is a hybrid position, meaning that you will need to live within easy driving distance to our Technology Center in Columbia, Maryland.

Develop and advance our offline mapping and reconstruction pipeline, driving accuracy and robustness across the hardest capture scenarios - textureless walls, highly reflective surfaces, featureless geometry, and large-scale scenes.
Build and maintain evaluation methodology grounded in real-world captures - covering feature-rich, textureless, and reflective environments - not synthetic benchmarks alone.
Collaborate closely with the SLAM and real-time mapping team to share components and ensure offline improvements feed back into the broader reconstruction platform.
Quidient is seeking a Senior Offline Mapping Engineer to own and advance the accuracy and robustness of our offline mapping and 3D reconstruction systems.

Deep working knowledge of multiview geometry, bundle adjustment, nonlinear estimation, and - critically - the practical failure modes of each.
Real experience with sensor calibration on real hardware.
Must-Have Qualifications:
Master's, or PhD in Computer Science, Computer Vision, Robotics, or a related field - or equivalent demonstrated experience. This is a Senior-to-Staff level role.
Significant hands-on experience building or substantially improving an offline SfM, multi-view stereo, or dense reconstruction system in production - not just research prototypes.
Strong C++ and Python.
Hands-on ability to design, train, and integrate deep learning components (learned matching, depth estimation, feature extraction) into a classical reconstruction pipeline using PyTorch or equivalent.
Willingness to work on-site in Columbia, MD, in a hybrid capacity.
Meet Quidient, customer, and government security requirements, which may include, but are not limited to a background check, citizenship verification, and Criminal Justice Information Services verification.
Nice-to-Have Qualifications:
Published or shipped work combining learned and classical methods in 3D vision pipelines.

Experience in fast-paced or startup environments.
Prior work on reconstruction of textureless, reflective, or geometrically challenging environments.
Expertise in neural scene representations (NeRF, Gaussian Splatting, or similar).
Experience with large-scale numerical optimization.
Contributor to open-source SfM, MVS, or 3D reconstruction projects (COLMAP, OpenMVS, or similar).
Track record of shipping mapping or reconstruction systems at production scale.

Annual bonus and equity as appropriate.
Health insurance
Life & disability insurance
Paid holidays & generous PTO
Opportunities for bonuses, equity, and career growth
Design and integrate deep learning methods (learned feature matching, monocular depth priors, learned outlier rejection) alongside classical SfM and MVS components to close the last 10% of reconstruction quality.
Stay current with the deep learning and 3D vision literature, applying good judgment about which methods are production-viable and which are benchmark artifacts.

Employer Statement
Quidient is an Equal Opportunity Employer.
Quidient will consider all qualified applicants without regard to race, color, religion, creed, sex, sexual orientation, gender identity, marital status, national origin, age, veteran status, disability, or any other classification protected by applicable state, federal, or local laws.
Equal Opportunity Employer Statement

Quidient, customer, and government security requirements, which may include, but are not limited to a background check, citizenship verification, and Criminal Justice Information Services verification

This listing is sourced directly from Quidient's careers page and normalized into a canonical job model.