Model AI Artist

Workman Labs; Greater London; Hybrid; GBP 70,000 - 120,000; Full time

Job summary

DNEG VFX in London is seeking a researcher to train and fine-tune ML models for hyperrealistic synthetic media, with emphasis on facial likeness and realism. You will curate datasets, collaborate with R&D, and apply in-house and open-source tools in a fast-paced VFX environment.

Ideal candidates bring proven ML training experience (GANs/Stable Diffusion), UNIX/Linux familiarity, and strong teamwork with a passion for cutting-edge AI workflows.

Qualifications

• Proven experience training ML models (GANs, Stable Diffusion, or similar).
• Familiarity with UNIX/Linux environments.
• Critical eye for facial likeness and visual quality.
• Excellent teamwork and communication skills; strong problem-solving.

Responsibilities

• Train and fine-tune ML models to generate hyperrealistic synthetic media.
• Curate, manage, and optimise datasets for high-quality, lifelike outputs.
• Diagnose and solve challenges using in-house and open-source technologies.
• Manage multiple model training processes simultaneously and track progress.
• Critically evaluate results with a focus on facial likeness and realism.
• Collaborate with R&D on model training techniques; stay on top of emerging AI research, tools, and workflows.

Skills

GANs training

Stable Diffusion

UNIX/Linux

Facial likeness

Python

Teamwork

ML programming

Tools

Nuke

Job description

Trains and develops generative ML models at DNEG VFX to create hyperrealistic visual outputs, working with developers, VFX artists, and AI teams to enhance the studio's proprietary tools.

Location

London, United Kingdom

—

Seniority

—

Compared with 15 other Research roles: Common across similar roles Unique to this role

What you'll do

Responsibilities

• Train and fine-tune ML models to generate hyperrealistic synthetic media
• Curate, manage, and optimise datasets for high-quality, lifelike outputs
• Diagnose and solve challenges using in-house and open-source technologies
• Manage multiple model training processes simultaneously and track progress Common
• Critically evaluate results with a focus on facial likeness and realism Unique
• Collaborate with R&D on model training techniques; stay on top of emerging AI research, tools, and workflows Common

What you'll need

Experience

• Proven experience training ML models (GANs, Stable Diffusion, or similar) Common
• Familiarity with UNIX/Linux environments Unique
• Critical eye for facial likeness and visual quality Unique
• Excellent teamwork and communication skills; strong problem-solving
• Bonus: VFX or compositing experience (Nuke), Python and ML programming, face-swap workflows