Founding Multimodal Researcher

Stealth GenAI startup (Headquarters: NYC ONSITE)

GenAI generative media multimodal reasoning CV image generation video generation research PyTorch founding team startup AI ML Deep Learning Computer Vision Multimodal AI preseed VC AI Engineer Data Science

**Company Overview:**
Join a stealth-mode GenAI startup in NYC, backed by top VCs and AI leaders. We're advancing the state-of-the-art in generative media with a unique technology. Our founding team includes experienced AI leaders from companies like Meta/FAIR (involved in projects like PyTorch, CICERO, SEER, ESMFold), committed to building innovative and prosocial teams. We've recently closed our preseed funding and are rapidly building our core research group.

**Role Description:**
This is a unique opportunity to be part of the founding researcher cohort of a deeply innovative team. We are seeking Founding Multimodal Researchers to join our initial group. This role sits at the boundary of fundamental and applied research, focusing on multimodal reasoning and generative media (images, video, etc.). You'll play a critical role in defining and executing our research agenda, contributing directly to our core technology, which no one else is building.

**Responsibilities:**
*   Conduct cutting-edge research in multimodal AI and generative models.
*   Design, implement, and evaluate novel algorithms and deep learning models.
*   Collaborate closely with the founding team to translate research breakthroughs into practical applications.
*   Stay abreast of the latest advancements in AI, particularly in generative models, computer vision, and multimodal learning.
*   Potentially publish research findings in top-tier conferences and journals.
*   Contribute to the company's intellectual property and potentially open-source projects.

**Ideal Candidate:**
*   Proven research experience in Computer Vision (CV), image generation, or video generation domains.
*   Demonstrated track record of impactful research, ideally through publications (e.g., NeurIPS, ICML, CVPR, ICCV) and/or significant open-source artifacts (models, libraries, datasets).
*   Strong understanding of deep learning principles and architectures (Transformers, Diffusion Models, GANs, VAEs, etc.).
*   Proficiency with deep learning frameworks like PyTorch.
*   Excellent programming skills (Python preferred).
*   M.S. or Ph.D. in Computer Science, AI, or a related field, or equivalent research experience.
*   Passionate about building foundational AI technology in a fast-paced, collaborative startup environment.
*   Ability to work onsite in NYC.