Member of Technical Staff - Diffusion Model

Embedding VC

Posted 4 months ago, valid for 5 days

San Francisco, San Francisco 94102, CA

Competitive

Full Time

By applying, a Sonicjobs account will be created for you. Sonicjobs's Privacy Policy and Terms & Conditions will apply.

Sonic Summary

Moonlake is seeking a candidate to develop AI for creating world simulations, focusing on modeling and architecture for various media formats.
The role involves building and refining diffusion architectures and working with multi-modal encoders and conditioning signals.
Candidates should have experience in large-scale diffusion training and optimizing sample quality against compute trade-offs.
The position requires familiarity with techniques such as ControlNet and building editing and personalization pipelines.
The salary for this role is competitive, and applicants should have at least 3 years of relevant experience.

Introducing Moonlake, AI for creating world simulations.

Modeling & architecture

Build and iterate on 2D/3D/image/video/audio diffusion architectures
Work on conditioning: text/image/pose/layout/control signals, multi-modal encoders, guidance strategies.

Training & optimization

Large-scale diffusion training
Improve sample quality vs. compute trade-offs: better objectives, distillation, consistency/one-step models.

Control & alignment

Techniques like ControlNet, LoRA, IP-Adapters, adapters for style/identity/geometry/control.
Build editing, inpainting, and personalization pipelines (DreamBooth, custom subject/style tuning).

We are committed to being an on-site, in-person team currently based in San Mateo

Learn more about this Employer on their Career Site

Apply now in a few quick clicks

By applying, a Sonicjobs account will be created for you. Sonicjobs's Privacy Policy and Terms & Conditions will apply.