Job Title
Generative AI Technical Artist (ComfyUI / AI Content Pipeline)
Location
Kuala Lumpur (Hybrid / Remote optional for strong candidates)
About Us
Byond Asia is building the HoloMe OS—an AI operating system that bridges intelligence with the physical world. We deploy hyper-realistic digital humans and AI-driven interfaces across film, media, retail, and public environments.
We are now expanding our AI-powered content production capabilities, working closely with film directors, producers, and creative teams to create next-generation visual content using generative AI pipelines.
Role Overview
We are looking for a Generative AI Technical Artist who can operate at the intersection of film production and AI engineering.
This role is responsible for translating creative direction into high-quality AI-generated visuals and video, using tools like ComfyUI, Higgsfield, and related generative AI platforms.
You will work directly with directors and producers to build workflows, generate content, and refine outputs for production use.
Key Responsibilities
1. AI Content Production
- Generate high-quality images, sequences, and video content using ComfyUI / AI tools
- Translate storyboards, scripts, and mood boards into AI-generated outputs
- Maintain visual consistency (characters, lighting, style) across scenes
2. Workflow & Pipeline Development
- Build and optimize node-based workflows (ComfyUI)
- Integrate models such as:
- SDXL / Stable Diffusion
- ControlNet
- LoRA / IPAdapter
- Design reusable pipelines for scalable production
3. Prompt Engineering & Creative Translation
- Convert director input into structured prompts and workflows
- Iterate rapidly based on feedback
- Ensure cinematic quality in composition, lighting, and framing
4. AI Video & Motion Generation
- Work with AI video tools (Runway, Pika, Higgsfield, etc.)
- Handle:
- Motion consistency
- Scene transitions
- Temporal stability
5. Post-Production & Enhancement
- Refine outputs using:
- Photoshop / After Effects / DaVinci Resolve
- Perform:
- Upscaling
- Inpainting / outpainting
- Compositing AI assets into production footage
6. R&D and Innovation
- Test new AI models and tools
- Improve workflow efficiency and output quality
- Contribute to internal AI production playbooks
Requirements
Technical Skills
- Strong experience with ComfyUI or node-based AI workflows
- Advanced prompt engineering skills
- Familiarity with:
- Stable Diffusion ecosystem (SDXL, LoRA, ControlNet)
- AI image-to-video workflows
- Basic understanding of GPU workflows and performance optimization
Creative Skills
- Understanding of film language:
- Shot composition
- Lighting
- Color grading
- Ability to interpret:
- Storyboards
- Mood boards
- Creative direction
Tools & Software
- ComfyUI / Higgsfield (or equivalent)
- Photoshop / After Effects / DaVinci Resolve
- AI tools: Runway, Pika, or similar
Soft Skills
- Ability to work directly with directors and producers
- Strong problem-solving and iteration mindset
- Ability to handle fast-paced production cycles
Nice-to-Have (Strong Advantage)
- Experience training LoRA / custom AI models
- Basic Python or automation scripting
- Experience in:
- VFX
- Film production
- Motion graphics
- Familiarity with real-time engines (Unreal Engine)
What Success Looks Like
- Ability to deliver production-ready AI visuals
- Build reusable workflows that reduce production time
- Maintain high consistency and cinematic quality
- Act as a bridge between creative vision and AI execution
Why Join Us
- Work on cutting-edge AI + film production workflows
- Be part of building a new category: AI for physical + visual content
- Collaborate with top creatives, directors, and AI engineers
- Opportunity to shape the future of digital humans and AI storytelling
How to Apply
Please submit:
- Portfolio (AI-generated work / ComfyUI workflows preferred)
- Brief explanation of your workflow process
- Examples of before after refinement
