---
title: 'Research Scientist (diffusion) at Genmo'
canonical: 'https://feeny.ai/job/research-scientist-diffusion-genmo-san-francisco-7d4n8smdbgqd'
type: 'job'
last_seen: '2026-09-12'
---

# Research Scientist (diffusion) at Genmo

- **Company:** Genmo
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Posted:** 2026-09-08
- **Last confirmed live:** 2026-09-12
- **Apply:** https://jobs.ashbyhq.com/genmo/0f8462cc-c351-41b0-a794-3558c63646e2

## Job description

We are Genmo, a research lab developing the world’s most sophisticated video world models to understand, simulate, and interact with the physical world. Our mission is to unlock the right brain of AGI. Join us in advancing physical intelligence and enabling robots to learn and act in a changing world. Role overview: We are seeking an exceptional Research Scientist to join our team, focusing on developing cutting-edge diffusion models for text-to-video generation. In this role, you will be at the forefront of innovation, creating novel architectures and algorithms that transform written descriptions into stunning, coherent video content.

Key responsibilities:

- Lead research initiatives in advanced diffusion models for text-to-video generation, focusing on improving visual quality, temporal consistency, and semantic fidelity
- Develop and implement state-of-the-art algorithms for translating textual descriptions into dynamic video content
- Design and conduct rigorous experiments to validate new ideas and evaluate model performance
- Collaborate with cross-functional teams to integrate research breakthroughs into our production pipeline
- Stay at the cutting edge of the field by regularly reviewing academic literature and attending top-tier conferences
- Contribute to the research community through high-quality publications and open-source contributions
- Mentor junior researchers and foster a culture of innovation within the research team
- Work closely with product teams to align research directions with user needs and market opportunities

Qualifications:

- Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, or a closely related field
- Must have:
- Strong publication record in top-tier conferences (e.g., CVPR, ICCV, NeurIPS, ICML) with a focus on generative models, particularly diffusion models
- Extensive experience implementing and optimizing large-scale generative models for image or video tasks
- Deep understanding of state-of-the-art techniques in text-to-image and text-to-video generation
- Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow
- Excellent communication skills with the ability to explain complex technical concepts to diverse audiences
- Proven ability to work collaboratively in a team environment
- Ideal candidate will have:
- Postdoctoral or industrial research experience in generative AI for video
- Hands-on experience with text-to-video generation projects
- Expertise in other generative model architectures (e.g., GANs, VAEs) and their applications to video
- Experience working with large-scale datasets and distributed computing environments
- Track record of successful collaboration with product teams on technology transfers
- Familiarity with video codecs, compression techniques, and perceptual quality metrics
- Contributions to open-source projects in the field of generative AI

Additional information The role is based in the Bay Area (San Francisco). Candidates are expected to be located near the Bay Area or open to relocation. Genmo is an Equal Opportunity Employer. Candidates are evaluated without regard to age, race, color, religion, sex, disability, national origin, sexual orientation, veteran status, or any other characteristic protected by federal or state law. Genmo, Inc. is an E-Verify company and you may review the [Notice of E-Verify Participation](https://drive.google.com/file/d/1urlF3XKQTw83aJfpMKMwrUP1E1mUlNTO/view?usp=sharing) and the [Right to Work posters in English and Spanish](https://drive.google.com/file/d/1ZD4zax6Li8oTN_VHd9w3rpFPoWeaeGVO/view?usp=drive_link).

## About Genmo

## Company Overview
- **One-liner**: Genmo is an AI research lab developing open-source state-of-the-art video generation models to unlock visual understanding for artificial general intelligence.
- **Entity Type**: Private (Series A, raised $58.4M total)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2022 (GitHub organization created December 2022) [github.com](https://github.com/genmoai)
- **Founders**: Paras Jain (Co-founder and CEO) [linkedin.com](https://www.linkedin.com/company/genmoai)

## Core Business
- Primary industry: Artificial intelligence / Generative media
- Target customers: B2B & B2C – developers, researchers, and content creators who use open-source models or the company’s interactive playground
- Mission or purpose: “Building open, state-of-the-art models for video generation towards unlocking the right brain of AGI.” [genmo.ai/careers](https://www.genmo.ai/careers)

## Products & Services
- **Mochi 1**: Open-source text-to-video model that turns written concepts into visual stories. Available via GitHub and ComfyUI for local customization and inference. [genmo.ai](https://www.genmo.ai/)
- **Playground**: Interactive web platform for testing and exploring the capabilities of Mochi without needing to run the model locally.
- **Research Publications**: The lab publishes interpretability and performance research on video diffusion models (e.g., internal behavior analysis of open-source video models). [linkedin.com](https://www.linkedin.com/company/genmoai)

## Market Standing
- **Valuation/Market Cap**: Not publicly available
- **Key Metric (Funding)**: $58.4M total funding across two rounds – a $30M venture round (Feb 2024) and a $28.4M Series A (Oct 2024), both led by New Enterprise Associates (NEA). [linkedin.com](https://www.linkedin.com/company/genmoai)
- **Notable Investors/Partners**: New Enterprise Associates (NEA)
- **Growth Signals**: 
  - Rapidly growing GitHub stars – Mochi repository has over 3,600 stars. [github.com](https://github.com/genmoai)
  - Recently hired several PhD-level researchers (Yue Fan, Yao Fu, Shyam) and a Member of Technical Staff. [linkedin.com](https://www.linkedin.com/company/genmoai)
  - Active job postings for research, engineering, and design roles (5 open positions as of mid-2025). [jobs.ashbyhq.com](https://jobs.ashbyhq.com/genmo)

## Competitive Advantages
- **Open‑source leadership**: Mochi 1 is considered a new state‑of‑the‑art in open text‑to‑video, offering a transparent alternative to closed models.
- **Research‑first culture**: The team focuses on fundamental advances in video world models, with published interpretability work.
- **Early mover in open‑source video generation**: Few competitors offer a comparable open‑source video model with active community and playground.

## Strategic Focus
- Continue advancing the capabilities of video world models to understand the physical world.
- Expand the open‑source ecosystem around Mochi, enabling broader customization and community contributions.
- Hire top research scientists (diffusion, post‑training) and engineering talent (GPU performance, research engineering) to accelerate model development. [genmo.ai/careers](https://www.genmo.ai/careers)

## Why Work Here
- **Benefits**: Fully paid health, dental, and vision insurance; 4% 401(k) matching; unlimited PTO and sick time; daily free lunch and dinner; commuter subsidy. [genmo.ai/careers](https://www.genmo.ai/careers)
- **Culture**: Small, research‑driven team (approx. 11 employees) with a flat structure and direct impact on cutting‑edge AI.
- **Office & Remote**: San Francisco HQ; roles listed as “San Francisco HQ · Full Time” – likely requires in‑office presence with commuter support.
- **Engineering culture**: Opportunity to work on large‑scale distributed training, GPU optimization, and open‑source contributions. Recent hires from top labs (Cohere, Leonardo.Ai, Microsoft, NVIDIA). [linkedin.com](https://www.linkedin.com/company/genmoai)

## Sources
1. [genmo.ai](https://www.genmo.ai/) – Company homepage, product overview, open source details
2. [genmo.ai/careers](https://www.genmo.ai/careers) – Careers page, benefits, open roles
3. [linkedin.com](https://www.linkedin.com/company/genmoai) – Company financials, headcount, recent hires, office locations
4. [github.com](https://github.com/genmoai) – GitHub organization, Mochi repository stars and description
5. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/genmo) – Active job listings (Research Scientist, GPU Engineer, Founding Product Designer)

## Other roles at Genmo

- [Research Scientist (post-training)](https://feeny.ai/job/research-scientist-post-training-genmo-san-francisco-34hk5d2bfb26) — San Francisco, CA
- [Research Engineer (New Grad)](https://feeny.ai/job/research-engineer-new-grad-genmo-san-francisco-vj3dwx33v5ry) — San Francisco, CA
- [GPU Performance Engineer](https://feeny.ai/job/gpu-performance-engineer-genmo-san-francisco-5bh8v1qprvfz) — San Francisco, CA
- [Founding Product Designer](https://feeny.ai/job/founding-product-designer-genmo-san-francisco-sats5vbhy81z) — San Francisco, CA