3D Vision & Localization Research Engineer

Niantic; Greater London; Hybrid; GBP 90,000 - 140,000; Full time

Job summary

Niantic Spatial in London is seeking a Research Engineer to advance Geospatial Visual Localization, enabling people and robots to localize anywhere on the planet. You will collaborate with researchers in 3D vision and ML, train large multi-modal models, and deploy them to production for broad real-world use.

The role involves handling heterogeneous data from phones, drones, and satellites, with an emphasis on robustness across locations, weather, and capture quality.

Qualifications

• Strong grounding in 3D computer vision, deep learning, robotics, photogrammetry, or related field.
• Experience with multi-view geometry and camera pose estimation, SfM, SLAM, georeferencing.
• Knowledge of transformers for 3D vision and multi-modal attention.
• Knowledge of geospatial data and coordinate reference systems.
• Ability to formulate real-world problems and evaluate solutions rigorously.
• Strong Python skills and experience training DL models at scale (PyTorch, NumPy, SciPy).
• Strong software engineering skills to deploy research prototypes.
• Excellent written and verbal communication and cross-disciplinary collaboration.

Responsibilities

• Design, implement, and evaluate novel visual localization algorithms, combining 3D vision and deep learning.
• Train large models on multi-modal data at scale, and build the benchmarks that measure their accuracy and robustness.
• Develop robust solutions for difficult real-world conditions: noisy or denied GPS, changing appearance, varying capture quality, large geographic extents, and imperfect reference maps.
• Work side-by-side with leading researchers in visual localization, 3D computer vision, and mapping, as well as engineering and product teams, to identify the highest-impact problems and turn research into end-to-end solutions that operate at production scale.
• Communicate results clearly through technical writing, design reviews, internal presentations, and publications.

Skills

3D computer vision

Deep learning

Robotics

Photogrammetry

Multi-view geometry

Camera pose estimation

SLAM

Georeferencing

Point-cloud registration

Sensor fusion

Transformer models for 3D vision

Geospatial data

Python

PyTorch

NumPy

SciPy

Software engineering

Research-to-Deployment

Communication

Tools

PyTorch

NumPy

SciPy

Job description

Niantic Spatial in London is seeking a Research Engineer to advance Geospatial Visual Localization, enabling people and robots to localize anywhere on the planet. You will collaborate with researchers in 3D vision and ML, train large multi-modal models, and deploy them to production for broad real-world use.

The role involves handling heterogeneous data from phones, drones, and satellites, with an emphasis on robustness across locations, weather, and capture quality.