AI Research Assistant for Local, Artist‑Driven Animation

Nanyang Technological University Singapore; Singapore; On-site; SGD 33,000 - 50,000; Full time

Job summary

NTU invites applications for a Research Assistant to work on a residency project with ADM to develop a local AI workflow for a hand-drawn animation artist. The role focuses on building a privacy-safe, cloud-free pipeline using ComfyUI and open-source tools, enabling the artist to operate a simple local setup.

You will set up models, train local LoRAs/ControlNets, and assemble a lightweight interface (Gradio) so the workflow is accessible to a non-technical collaborator.

Qualifications

• Bachelor's degree in Animation, Film Studies, Media Studies or related discipline.
• Hands-on experience with ComfyUI and local AI deployments.
• Ability to translate artistic intent into technical parameters.
• Willingness to support a non-technical artist during residency.

Responsibilities

• Set up and optimize local, open-source AI models (Stable Diffusion/ComfyUI) on high-end workstation hardware, with no cloud dependency.
• Train local LoRAs and ControlNets on a curated archive of the artist's analogue sketches and scans.
• Package the ComfyUI workflow into a simple, easy-to-run form (presets, node groups, or a lightweight Gradio front-end).
• Provide on-the-ground technical support during Prof. Krumme's residency (14 Sept – 13 Nov 2026).
• Document the system architecture and user-testing feedback for the final research report.

Skills

ComfyUI / local AI deployment

LoRA training

ControlNet training

GPU/VRAM optimization

Interface prototyping (Gradio)

Artist collaboration

Education

Bachelor's degree in Animation, Film Studies, Media Studies or related

Tools

ComfyUI

Automatic1111

Forge

Gradio

Job description

NTU invites applications for a Research Assistant to work on a residency project with ADM to develop a local AI workflow for a hand-drawn animation artist. The role focuses on building a privacy-safe, cloud-free pipeline using ComfyUI and open-source tools, enabling the artist to operate a simple local setup.

You will set up models, train local LoRAs/ControlNets, and assemble a lightweight interface (Gradio) so the workflow is accessible to a non-technical collaborator.