The Role You'll work with tools like ComfyUI, Griptape, and Nuke, alongside Python and the latest open-source generative models — including MiniMax H3, LTX 2.5, FLUX, Wan, Qwen Image, and whatever comes next.
The Role Involves
- Building and improving ComfyUI workflows for image and video
- Building agentic workflows with Griptape
- Testing and integrating new models such as MiniMax H3 and LTX 2.5
- Writing Python tooling and custom nodes where required
- Developing workflows around:
- LoRAs
- ControlNets
- Reference conditioning
- Relighting
- Upscaling
- Video-to-video
- Emerging techniques
- Turning experiments into reliable production workflows
- Keeping up with new models and quickly figuring out what's actually useful
What We're Looking For You should have a background in technical development, VFX/compositing, technical art, generative AI, or a similar technical-creative field.
You should be comfortable with:
- Python
- Git / GitHub
- Open-source AI tools and models
- Basic Linux / command-line workflows
- Generative image and video models
- Troubleshooting technical workflows
Important You must have hands-on experience with at least ONE of the following:
- Nuke
- ComfyUI
- Griptape
If you haven't worked with any of these tools, please do not apply.
To be considered for the position, candidates must have relevant experience in at least one of the specified areas. Applications that do not meet this requirement will not be considered.
You do not need to know all three. Robust experience with one, combined with the ability to learn the others, is enough.
Bonus Experience with any of the following is a plus:
- PyTorch
- Custom ComfyUI nodes
- LoRA / ControlNet training
- Hugging Face
- Docker
- CUDA
- Cloud GPUs
- MiniMax H3
- LTX 2.5
- FLUX
- Wan
- Qwen Image
- Nuke or other VFX tools