In this role, you'll own the post-training pipeline for our multimodal models end to end — from data strategy and reward modeling to preference optimization, distillation, and safety tuning — across image, editing, and video
Job Summary
In this role, you'll own the post-training pipeline for our multimodal models end to end — from data strategy and reward modeling to preference optimization, distillation, and safety tuning — across image, editing, and video.
You'll drive measurable gains in model quality, build the infrastructure that lets the whole research team iterate fast, and push the state of the art in what it means to align a generative model to human intent.
We're a distributed team with real offices that people actually use, and we'll discuss what this will look like for the role during our interview process.
Matching Summary
In this role, you'll own the post-training pipeline for our multimodal models end to end — from data strategy and reward modeling to preference optimization, distillation, and safety tuning — across image, editing, and video.
Skills & Requirements
Must-have
own post-training pipeline end to end
advance post-training techniques
work across modalities
build personalization capabilities
design and maintain infrastructure
identify and close quality gaps
Nice-to-have
research excellence
open science
expand human creativity
low ego
bold
kind
Key Requirements
owned post-training for a frontier generative model
deep experience across post-training stack
comfortable working across modalities
strong PyTorch fluency
experience with distillation or building eval pipelines is a plus