companyGenPeach AI logo

AI Research Engineer - Image/Video Foundation Models

On-site Full-time

Clicking Apply Now takes you to AutoApply where you can tailor your resume and apply.


Unlock Your Potential

Generate Job-Optimized Resume

One Click And Our AI Optimizes Your Resume to Match The Job Description.

Is Your Resume Optimized For This Role?

Find Out If You're Highlighting The Right Skills And Fix What's Missing

Experience Level

Experience

Qualifications

Candidates should possess a strong background in AI and machine learning, with proficiency in image and video processing techniques. A solid understanding of neural network architectures and experience with large-scale model training is essential. Effective collaboration skills and the ability to work in a fast-paced, innovative environment are crucial.

About the job

About GenPeach AI

GenPeach AI is a pioneering research lab dedicated to developing vertical multimodal foundation models aimed at creating hyper-realistic human representations in images and videos. Our mission is to empower human creativity through advanced AI tools rather than replace it.

We build our models from the ground up, utilizing proprietary datasets at an expansive scale, innovative architectures and training methodologies, extensive GPU resources, and seamless product integration to expedite the delivery of our research to end users.

Our team consists of approximately 10 highly skilled professionals, guided by advisors from Google DeepMind and supported by prominent AI-focused investors and advisors from OpenAI, Meta AI, Microsoft AI, Project Prometheus, and Fal. Collectively, our team and advisors have significantly contributed to groundbreaking models such as Meta’s Imagine/MovieGen, OpenAI’s Sora, Google’s Veo, and Gemini.

About the Team

You will become a key member of the research team, focused on advancing image/video generation and multimodal understanding. Collaborating closely with fellow Research Engineers, Scientists, and Founders, you will transform innovative research into scalable training processes, robust evaluations, and production-ready systems.

About the Role

We are seeking an AI Research Engineer to contribute to the end-to-end development and scaling of GenPeach’s foundational models. Your responsibilities will include the implementation of new model concepts and training methodologies, managing critical aspects of the training stack that influence quality and efficiency, and navigating production constraints.

This role is hands-on with a high degree of ownership, where you will write research-quality code that is vital for production.

In this role, you will

  • Develop and refine image/video generative model concepts (architecture, loss functions, conditioning, sampling, distillation, post-training adjustments)

  • Oversee training performance comprehensively (distributed training, throughput, memory management, stability, debugging scaling issues)

  • Establish and enhance the experimental workflow (evaluations, ablation studies, reproducibility tools, reporting, decision-making processes)

  • Create and optimize VLMs for image/video captioning (data preparation, training strategies, model variations, evaluation)

  • Conduct high-frequency research: review literature as needed, implement concepts, and validate findings empirically

About GenPeach AI

GenPeach AI is at the forefront of AI research, dedicated to building innovative multimodal models that enhance human creativity. With a team of highly skilled professionals and advisory support from industry leaders, GenPeach AI is committed to delivering cutting-edge solutions that redefine the possibilities of AI in image and video generation.

Similar jobs

Tailoring 0 resumes

We'll move completed jobs to Ready to Apply automatically.