Rodeo
Get started

Stanford Translational AI lab

Postdoctoral Research Fellow: 3D Human Understanding, Motion Foundation Models, and Video Understanding

Stanford
Posted 1 day ago
Sign up to applySee more jobs like this

How your CV stacks up

1Upload CV
2Analyse CV
3Improve CV

Upload your CV to see how well it fits this job role

?%

Openings

Postdoctoral Research Fellow: 3D Human Understanding, Motion Foundation Models, and Video Understanding

Overview

We are looking for an exceptionally talented Postdoctoral Research Fellow to join our interdisciplinary team at the forefront of machine learning, computer vision, 3D human understanding, motion prediction, and video understanding. This position is hosted by the Stanford Translational AI (STAI) Lab in collaboration with the Stanford Vision and Learning (SVL) Lab within the Computer Science Department. These dynamic research groups are renowned for their groundbreaking contributions to artificial intelligence, computer vision, and deep learning, particularly in human motion and video understanding.

Project Description

The successful candidate will work on cutting-edge projects aimed at building 3D human pose estimation/mesh reconstruction, multimodal motion generation (text/audio driven) and multimodal video understanding (text/audio). The postdoc will contribute to the development of advanced AI models that enable a deeper understanding of human motion and behavior in real-world environments. These models will be applied to various domains such as healthcare, human-computer interaction, sports analysis, and entertainment.

Key Projects May Involve

  • Developing motion foundation models for 3D human motion generation, pose estimation, and human activity recognition.
  • Advancing video understanding models for tasks such as action recognition, scene understanding, and human-object interaction.
  • Leveraging multi-modal data (e.g., video, motion capture, depth sensors) to build robust, generalizable models of human behavior and interactions.
  • Exploring novel self-supervised and transfer learning techniques to improve the scalability and adaptability of these models.

Reasons to use Rodeo

I’m in my final year doing Economics and I don’t know whether to apply for grad schemes now or do a masters first. What do you think?

Honest answer — it depends on where you want to end up. A lot of top grad schemes (Big 4, civil service, banking) don’t need a masters. Let’s look at the ones you’d be competitive for now, and we can decide if a masters actually adds anything.

Also worth knowing: most autumn 2026 applications are open now. Timing matters more than you think.

Start with a chat, not a search bar

Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.

P

Graduate Consultant — 2026 Scheme

PwC·London, UK
£35,000/yr

Why you're a good match

Strong

Your economics background and your summer at a regional bank line up with what PwC looks for on the consulting scheme. Applications close in four weeks.

See breakdown
Save jobNot relevant
View details

It searches the market for you

Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.

Why you're a good match

You’ve got the grades and the economics background, and your bank internship is exactly the experience this scheme looks for. Apply soon — deadlines close within the month.

See breakdown
Strong

Experience fit

Your summer at the bank plus your econometrics coursework map directly to the day-one responsibilities on this scheme — client modelling, market briefings, and deal support.

See breakdown
Strong

Only hits

No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.

Key Responsibilities

  • Conduct research in machine learning, computer vision, 3D human understanding, and video analysis.
  • Develop and implement algorithms for 3D human pose estimation, motion generation, and video understanding.
  • Design and train large-scale motion foundation models using multi-modal datasets.
  • Collaborate with a team of researchers and industry partners to apply these models in domains such as healthcare, robotics, and human-computer interaction.
  • Mentor graduate students (Ph.D. and MSc) in related research areas.
  • Publish findings in top-tier AI and computer vision conferences and journals.
  • Contribute to grant writing and proposal development to secure research funding.

Qualifications

  • Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field.
  • Proven track record of publications in high-impact journals and conferences including CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, and Nature.
  • Strong background in machine learning, computer vision, 3D human understanding, and video analysis.
  • Proficiency in Python, C++, or similar languages and experience with deep learning frameworks such as PyTorch or TensorFlow.
  • Experience with large-scale datasets and training motion or video-based models.
  • Excellent communication skills, both written and verbal, with a proven ability to work independently and collaboratively.

Get help with your application

Your very own career expert that helps elevate your application to the next level.

Get help applying for this job

Benefits

  • Competitive salary and benefits package.
  • Access to state-of-the-art facilities and computational resources at Stanford.
  • Opportunities for professional development and international collaboration with leading experts in the field.
  • Participation in international conferences and workshops, fostering academic and industrial partnerships.

Working Environment

As a postdoctoral researcher at Stanford University, you will be part of a vibrant intellectual community with access to world-class research facilities. Stanford offers numerous opportunities for interdisciplinary collaboration, professional development, and innovation. The university's global network of leading experts and industry partners will enhance your career growth and research impact.

Apply

Previous article: Postdoctoral Fellow Position in AI for Psychiatry: LLMs and Multimodal Foundation Models Prev

Next article: Postdoc Application: Medical Imaging, Biomedical Data Analysis, Machine Learning Foundation Models Next

Trusted by 25,000+ job seekers

“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”

Jessica, London

Get help applying for this job

Skills

Machine Learning
Computer Vision
3D Human Understanding
Video Understanding
Motion Prediction
Python
C++
PyTorch
TensorFlow
3D Human Pose Estimation
Mesh Reconstruction
Multimodal Motion Generation
Self-supervised Learning
Transfer Learning
Action Recognition
Scene Understanding

Location

Stanford, England, United Kingdom

Sign up to applySee more jobs like this