Gen AI Specialist

Workman Labs; Greater London; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

DNEG is seeking an applied expert in audiovisual generative AI to evaluate cutting-edge technologies, prototype proofs-of-concept, and act as the first testing contact for in-house research developments.

Remote across EMEA with London as a potential base, you will collaborate with research and development teams to advance GenAI workflows and ComfyUI integrations for scalable pipelines.

Qualifications

• Experience testing photoreal generative models for video applications.
• Proficient with Conda, git, dependency management and Python/PyTorch for adapting code.
• Experience managing large training datasets and understanding data curation impacts on models.
• Very proficient in ComfyUI for scalable workflows and shared environments.
• Nice to have: prior research/R&D or background in VFX, visual arts, or visually-driven tech.

Responsibilities

• Identify and evaluate cutting-edge GenAI technologies and workflows across open and closed-source ecosystems.
• Prototype proof-of-concept implementations aligned with company needs.
• Act as the first point of contact for implementing and testing in-house research developments.
• Offer research teams context and informed proposals drawing on product and creative insights.
• Build scalable ComfyUI workflows and maintain a shared, evolving ComfyUI environment.
• Present research findings to developers and creatives, highlighting strengths, weaknesses, and examples.

Skills

ComfyUI

Python/PyTorch

Conda

Git

Dependency management

Model tuning

Large training datasets

Hyperparameters

Onboarding artists

Tools

ComfyUI workflows

Job description

Applied expert in audiovisual generative AI at DNEG who evaluates cutting-edge technologies, prototypes proof-of-concept implementations, and acts as the first point of contact for testing in-house research. Hiring remotely across EMEA.

Location

London, United Kingdom

Remote

Seniority

—

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

What you'll do

Responsibilities

• Identify and evaluate cutting-edge GenAI technologies and workflows across open and closed-source ecosystems
• Prototype proof-of-concept implementations aligned with company needs Unique
• Act as the first point of contact for implementing and testing in-house research developments Unique
• Offer research teams context and informed proposals drawing on product and creative insights
• Build scalable ComfyUI workflows and help maintain a shared, evolving ComfyUI environment Unique
• Present research findings to developers and creatives, highlighting strengths, weaknesses, and examples Unique

What you'll need

Experience

• Professional experience testing and training photoreal generative models, ideally for video applications Common
• Confident with Conda, git, dependency management, and enough Python/PyTorch to adapt code to specific requirements
• Experience managing large training datasets and understanding how captioning, curating, and enhancing them affects the trained model Common
• Comfortable tweaking model tuning hyperparameters and understanding their effects
• Very proficient in ComfyUI: scalable workflows, custom nodes, shared environments Unique
• Deep engagement with GenAI communities across open and closed-source spaces
• Comfortable onboarding and training artists from other disciplines Unique
• Nice to have: prior research/R&D role; background as a creative or developer in VFX, visual arts, or a visually-driven tech company Unique