Computer Vision Researcher – Vision-Language Models & Spatial AI

About Niantic Spatial

At Niantic Spatial, we're building the future of geospatial AI.

Powered by a proprietary database of more than 30 billion posed images and a groundbreaking third-generation digital map, our mission is to develop spatial intelligence that helps both humans and machines better understand, navigate, and interact with the physical world.

Our high-fidelity mapping technology unlocks a new dimension of interaction, laying the foundation for AI systems that can truly comprehend and operate within real-world environments.

Join us as we build a living model of the world that people and machines can talk to.

About the Role

As a Computer Vision Researcher with experience in Large Language Models (LLMs), you will bridge the gap between 3D computer vision and language models, creating a unified framework that enables machines to reason about their surroundings.

By linking spatial geometry directly to language, you will help build systems capable of context-aware navigation and answering complex, open-ended questions about the physical world.

Responsibilities

• Lead research into cross-modal semantic grounding that connects 3D spatial features with language embeddings, enabling large geometry models (LGMs) to understand object relationships and environmental context

• Develop and deploy algorithms for continuous semantic understanding, allowing 3D maps to evolve and improve as new ground-level and aerial data is incorporated

• Build the "spatial brain" for embodied AI systems, enabling robots, drones, and autonomous machines to perform mission-level reasoning beyond simple navigation

• Define new multimodal benchmarks for measuring spatial common sense in language models, evaluating their ability to interpret and operate within complex 3D environments

• Serve as the technical leader for the London R&D hub by resolving architectural challenges and mentoring researchers working at the intersection of 3D computer vision and natural language processing

• Collaborate with product leadership to ensure the "Understand" API delivers meaningful value for enterprise customers across robotics, logistics, and field operations

Required Qualifications

• PhD (or equivalent) in Computer Vision, Machine Learning, Robotics, or a related field with a focus on multimodal or semantic understanding

• 4+ years of machine learning research experience with a proven track record of shipping models that bridge 3D vision and language

• Expert knowledge of:

  • 3D geometry

  • Structure-from-Motion (SfM)

  • SLAM

  • Visual Positioning Systems (VPS)

  • Transformer-based architectures and Vision-Language Models (VLMs)

• Multiple first-author publications at leading conferences such as:

  • CVPR

  • NeurIPS

  • ICLR

• Research focused on:

  • Vision-language models

  • Scene understanding

  • Semantic segmentation

• Strong implementation skills with production-quality research code in PyTorch or JAX

• Experience building and maintaining large-scale data pipelines

• Ability to work in the office three days per week

Preferred Qualifications

• Experience with Gaussian Splatting or NeRFs for semantic scene representation

• Background in robotics, including ROS or embodied AI systems operating in physical environments

• Experience with open-set recognition and zero-shot learning techniques

Candidate Privacy Policy

By submitting an application, candidates acknowledge that the information provided will be processed in accordance with Niantic Spatial's Privacy Notice for Job Applicants and Candidates.

Where required by law, applicants consent to the processing of information described in that notice, including any voluntarily disclosed information such as health or medical information, race or ethnicity, sexual orientation, and limited sharing with references and third parties involved in the hiring process.

Equal Employment Opportunity

Niantic Spatial is an equal opportunity employer.

All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations, and ordinances.

If you require reasonable accommodation during the application process, please contact your recruiter.