If you can look at a flat reference image and mentally “pull it into the real world,” this is your lane. You’ll build accurate, production-ready 3D assets from 2D material, document your decision-making, and iterate fast based on feedback so the work stays clean, consistent, and usable.
About Invisible Agency
Invisible supports companies by building scalable, high-quality operations. This freelance AI Trainer project relies on specialist creators to produce and evaluate high-quality outputs and help improve AI systems through expert-led work.
Schedule
Remote (United States).
Contract / freelance.
Hours vary based on your availability (you’ll report average weekly hours).
You provide your own secure computer and high-speed internet. No company benefits (contractor role).
What You’ll Do
Translate 2D reference images into precise 3D models with accurate geometry, proportions, and topology
Source additional reference material to resolve occlusions, unclear details, or incomplete imagery
Create high-quality assets across categories:
- Hard surface: vehicles, props, machinery
- Organic: humans (including realistic digital doubles), animals, plants, natural forms
- Environments & architecture: buildings, landscapes, set pieces, world assets
Iterate on models based on feedback, aligning with quality standards and artistic direction
Communicate your process clearly, including how you solved visual gaps and made modeling decisions
What You Need
Bachelor’s/Master’s in 3D Art, Animation, Game Design, Computer Graphics (nice), or equivalent professional experience
Proficiency with industry tools (Maya, Blender, ZBrush, Houdini, 3ds Max) and familiarity with UV/texturing workflows (Substance Painter, Mari)
Portfolio showing range across hard surface, organic, and environment work (film, games, AR/VR, interactive media a plus)
Strong grasp of anatomy, form, materials, and volumetric fidelity
Comfort in iterative pipelines and collaboration, with openness to feedback
Benefits
Pay rate: $22/hour
Remote, flexible contract work
Build portfolio-ready assets while contributing to the next generation of AI-assisted creation workflows
Small correction I’m going to make for clarity: this isn’t really “entry-level” if you’re expected to produce production-ready models across multiple categories. If you can truly do all three (hard surface + organic + environment) at a high level, you’re not a beginner, and you should make sure your portfolio screams that.
Happy Hunting,
~Two Chicks…