# ML Researcher - Posttraining

Hiring organization: [Krea AI](https://career.thegoodapps.co/organizations/krea-ai)

Canonical page: https://career.thegoodapps.co/jobs/557d978f-3ab8-4a9a-a76f-43cd964070ac

Listed on Krea AI's own careers site. Applications go to them directly.

- Employment type: full time
- Seniority: Senior
- Location: San Francisco, CA

## Summary

This role focuses on advancing the aesthetics and quality of Krea's image generation models through large-scale posttraining techniques, including preference optimization and reinforcement learning. It suits researchers with deep expertise in diffusion model finetuning and infrastructure who want to work on cutting-edge generative AI tools with a team that values both technical excellence and creative sensibility.

_Our summary, not Krea AI's wording._

## Skills named

PyTorch, Reinforcement Learning

## Required

- Proven posttraining work on diffusion models for image or video generation
- Large-scale model training, inference, and optimization experience
- Strong understanding of LLM and diffusion posttraining pipelines and algorithms
- Strong PyTorch proficiency
- Distributed training experience with FSDP, tensor parallelism, pipeline parallelism, and other parallelism strategies
- Low precision training and inference knowledge
- VLM model training experience
- Ability to identify model weaknesses and design concrete evaluations and reward functions

## Nice to have

- Knowledge of fast inference engines like vLLM and SGLang
- Understanding of RL frameworks like SLIME, MILES, Tinker, and Verl
- Experience with RL infrastructure optimization techniques
- Familiarity with related fields such as representation learning and robotics research

Apply on Krea AI's site: https://jobs.ashbyhq.com/krea/04d2889b-3cd6-498c-9653-0cd2e2d505fe/application