Machine Learning Engineer

at Krea AI · Multimodal · San Francisco, CA · Research

Machine Learning Engineer at Krea AI, focusing on large-scale training of foundation diffusion models for image and video generation, including controllability modules. The role involves developing novel research techniques and implementing them in production, optimizing data pipelines, and conducting experiments on HPC clusters.

What you'd actually do

  1. Train foundation diffusion models for image and video generation.
  2. Train controllability modules such as IPAdapters or ControlNets.
  3. Develop novel research techniques and put them into production.
  4. Conducting large-scale experiments on high-performance computing clusters, optimizing data pipelines for massive image datasets

Skills

Required

  • deep learning frameworks
  • distributed training paradigms
  • image models at scale
  • video models at scale

Nice to have

  • publications
  • open-source contributions
  • creative research directions

What the JD emphasized

  • large-scale image and video models training experiments
  • large-scale experiments
  • massive image datasets

Other signals

  • large-scale image and video models training experiments
  • Train foundation diffusion models for image and video generation
  • Develop novel research techniques and put them into production
Read full job description

About Krea

At Krea, we are building next-generation AI creative tools.

We are dedicated to making AI intuitive and controllable for creatives. Our mission is to build tools that empower human creativity, not replace it.

We believe AI is a new medium that allows us to express ourselves through various formats—text, images, video, sound, and even 3D. We're building better, smarter, and more controllable tools to harness this medium.

This job

We're looking for a machine learning engineers who can work on large-scale image and video models training experiments..

Some stuff you can do:

  • Train foundation diffusion models for image and video generation.
  • Train controllability modules such as IPAdapters or ControlNets.
  • Develop novel research techniques and put them into production.
  • Conducting large-scale experiments on high-performance computing clusters, optimizing data pipelines for massive image datasets

Example experience and skills we’re looking for

  • Proven track record in working with image or video models at scale (publications or open-source contributions a plus)
  • Strong background in deep learning frameworks and distributed training paradigms.
  • Ability to iterate rapidly, and propose creative research directions

A bit more about us

We’ve raised over $83M and are backed by world-class Silicon Valley investors such as Andreessen Horiwitz, and the cofounder of the Meta AI Research laboratory (FMK as Facebook AI Research) or founding members of OpenAI.