Geometric Deep Learning Research Scientist F/M
-
Contract type: Permanent contract
-
Work time: Full time
-
Location Meylan
About NAVER LABS Europe
NAVER LABS Europe is part of the R&D division of NAVER, Korea’s leading Internet portal and a global tech company with a range of services that include search, commerce, content, fintech, robotics and cloud.
About the team
The Geometric Deep Learning team is part of the vision group. With foundations rooted in multiple-view geometry, our mission is to conduct cutting-edge research for Spatial AI and Reasoning, towards efficient and robust perception of scenes through images and videos. The team is at the core of the foundational research lines of CroCo [1] self-supervised pretraining, that directly lead to the development of DUSt3R [2] and many of its follow-ups oriented towards accuracy and scalability like MASt3R [3,4], online real-time reconstruction [5] or integration of semantics [6].
In the Vision group, we conduct research to enable robots to understand and interact with their environment through advanced perception systems. We focus on visual perception, a fundamental capability for any intelligent system designed to engage with the world. Robots must perceive the structure, objects, and people in their surroundings to build a deeper understanding of their environment and effectively perform assigned tasks. Our research combines 3D vision, visual representation learning, self-supervised learning, and human behavior understanding to develop AI components that help robots navigate in 3D environments, detect and interact with surrounding objects and people, and continuously adapt when deployed in new environments.
The position
We are looking for a research scientist to join the Geometric Deep Learning team at NAVER LABS Europe.
With the help of our team of world experts, and thanks to our data, codebases and compute, the candidate will contribute to the next generation of feed-forward 3D reconstruction models with impactful academic research towards new capabilities, and concrete real-life applications.
Your activities may include :
- Conduct research on the next generation of 3D foundation model
- Help design new algorithms and proof-of-concept systems
- Train models for geometric perception at scale
- Validate their accuracy by running and analyzing large-scale experiments
- Showcase their performance and robustness with real-life demos
- Communicate about the advances made in both international academic and industrial contexts, in the form of scientific publications in top conferences, blogs, and internal reports
What we're looking for
A PhD in computer science, with a focus on 3D reconstruction and deep learning, including experience in feed-forward 3D reconstruction, transformer architectures and the Structure-from-Motion pipeline.
- A track record of research excellence, with contributions to major conferences and/or journals in computer vision (CVPR, ICCV, ECCV) and machine learning (NeurIPS, ICML, ICLR).
- The ability to work collaboratively within an international multidisciplinary team and to contribute to an inclusive team culture
- Excellent programming skills in Python and proficiency in PyTorch
- Experience with GPU computing and architectures.
- A deep understanding and substantial experience in high-performance computing is a plus
- Prior experience with multimodality and various sensors will be valued
Team Publications
The team regularly publishes in leading AI and robotics conferences. Recent publications include:
- CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow, Weinzaepfel - ICCV, 2023
- DUSt3R: Geometric 3D Vision Made Easy, Wang - CVPR, 2024
- Grounding Image Matching in 3D with MASt3R, Leroy - ECCV, 2024
- Mast3r-sfm: a fully-integrated solution for unconstrained structure-from-motion, Duisterhof - 3DV 2025
- Must3r: Multi-view network for stereo 3d reconstruction, Cabon - CVPR 2025
- PanSt3R: Multi-view Consistent Panoptic Segmentation, Zust - ICCV, 2025
What we offer
- We foster a collaborative environment dedicated to ambitious, multidisciplinary projects that translate advanced research into impactful, real-world solutions, supported by 30+ years of experience in AI and related fields.
- Flexible work/life balance.
-
We are an equal opportunity employer that hires based on skills, experience, and merit. We foster an inclusive and diverse workplace where all qualified candidates are considered fairly, regardless of background.
-
We’re based in Meylan, close to Grenoble, a city that offers the perfect balance of urban life, cutting-edge research and technology, and spectacular mountain landscapes that provide countless opportunities to relax, recharge, and enjoy the outdoors.
All applications will be carefully considered, even if not all required skills are met. We value diverse backgrounds and the potential of each candidate, and we offer training to support the development of necessary skills.
NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important ways to achieve these goals. Teamwork, focus and persistence are important values for us.
When applying for this position online, please don't forget to upload your CV and cover letter. Incomplete applications will not be considered.
NAVER LABS Europe is subject to French jurisdiction requiring organisations to stipulate that a job/internship is open to both women and men. None of our jobs/internships are gender specific.
References
Réf: 75ce9416-89b9-40e2-b7f2-346f9f409bc1