研究科学家实习生，视听对话场景生成

Meta（Meta Platforms）岗位：Research Scientist Intern, Audio-Visual Conversation Scene Generation (PhD) Responsibilities

Design and train video diffusion or flow-matching models for multi-person conversation scenes, generating audio and video together.

Develop ways to condition generation on 3D layout, group structure and egocentric camera trajectory.

Keep each person's identity consistent across frames and viewpoints, from one or several reference images.

Model natural conversational behavior: speech-driven faces and gestures, gaze, turn-taking and listener reactions.

Build evaluations for realism, audio-visual sync, identity consistency, and how closely the generated 3D positions and poses match the specified ones.

Use the generated data to train downstream egocentric perception models, and measure how much it helps.

Publish results at top venues together with Meta researchers.

Currently has, or is in the process of obtaining, a PhD in Computer Science, Electrical Engineering, Machine Learning or a related field

Research experience in generative modeling for video or images, with first-author publications at venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR or SIGGRAPH

Hands-on experience training or fine-tuning modern video diffusion or flow-matching models (e.g. DiT-based architectures), including conditioning methods such as adapters, ControlNet or LoRA

Experience with controllable generation from geometric or structural signals: camera pose, 3D layout, depth or human pose

3+ years experience with Python, Matlab, Pytorch, large-scale distributed GPU training or similar

Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment

Experience with joint audio-video generation, speech-driven talking heads or gestures, multi-speaker TTS, or lip sync

Research on modeling social interaction: conversational dynamics, gaze, turn-taking or group formations

Familiarity with egocentric perception and datasets (e.g. Ego4D, Ego-Exo4D, Aria), and with tasks such as active speaker detection or conversation grouping

Experience with 3D or 4D human and scene representations (e.g. SMPL-X, Gaussian splatting, NeRF) or multi-view-consistent video generation

Experience with synthetic data generation, game engines, or improving how well models trained on synthetic data perform on real data

Proven track record of achieving results as demonstrated in accepted papers at top computer vision and machine learning related conferences such as CVPR, ECCV, NIPS, ICASSP, InterSpeech etc

Meta builds technologies that help people connect, find communities, and grow businesses.

When Facebook launched in 2004, it changed the way people connect.

Apps like Messenger, Instagram and WhatsApp further empowered billions around the world.

Now, Meta is moving beyond 2D screens toward immersive experiences like augmented and virtual reality to help build the next evolution in social technology.

People who choose to build their careers by building with us at Meta help shape a future that will take us beyond what digital connection makes possible today—beyond the constraints of screens, the limits of distance, and even the rules of physics.

For those who live in or expect to work from California if hired for this position, please click here for additional information.

Individual compensation is determined by skills, qualifications, experience, and location.

Compensation details listed in this posting reflect the base hourly rate, monthly rate, or annual salary only, and do not include bonus, equity or sales incentives, if applicable.

In addition to base compensation, Meta offers benefits.

Learn more about benefits at Meta.

Meta is proud to be an Equal Employment Opportunity employer.

We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, reproductive health decisions, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, genetic information, political views or activity, or other applicable legally protected characteristics.

You may view our Equal Employment Opportunity notice here.

Meta is committed to providing reasonable accommodations for qualified individuals with disabilities and disabled veterans in our job application procedures.

If you need assistance or an accommodation due to a disability, fill out the Accommodations request form.

Take the first step toward a rewarding career at Meta.

Apply now APPLY NOW Find your role Explore jobs that match your skills and experience. Search by technology, team or location to find an opening that’s right for you. View jobs

Recruiters can view your conversations with AI. Using AI is optional and does not impact the outcome of your application process.Learn more about AI usage and settings.

We do not discriminate based upon race, religion, color, national origin, sex (including pregnancy, childbirth, reproductive health decisions, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, genetic information, political views or activity, or other applicable legally protected characteristics.

You may view our Equal Employment Opportunity notice here.

Meta is committed to providing reasonable support (called accommodations) in our recruiting processes for candidates with disabilities, long term conditions, mental health conditions or sincerely held religious beliefs, or who are neurodivergent or require pregnancy-related support.

If you need assistance or an accommodation due to a disability, fill out the Accommodations request form Notice regarding automated employment decision tools in New York City Learn more about this here.

©2026 Meta.

Currently has, or is in the process of obtaining, a PhD in Computer Science, Electrical Engineering, Machine Learning or a related field.

Research experience in generative modeling for video or images, with first-author publications at venues such as CVPR, ICCV, ECCV, NeurIPS, ICLR or SIGGRAPH.