We are seeking a talented and innovative Generative AI Engineer to join our team. You will develop, optimize, and deploy state-of-the-art generative models for diverse applications, including text generation, image synthesis, and audio processing. This role requires expertise in computer vision, machine learning, deep learning, and MLOps, with hands-on experience in GANs, VAEs, Transformers, and Diffusion Models. You will actively contribute to building AI tools for CGI animation and VFX pipelines, enabling scalable, creative, and efficient workflows across

departments including Asset Development, Rigging, Animation, Layout, Lighting, FX, Compositing, Editorial, and Rendering.

Key Responsibilities :

- Design, develop, train, and optimize generative models (GANs, VAEs, Diffusion Models, Transformer Models) across text, image, audio, and video domains :

1. 3D Reconstruction

2. Human Pose Estimation

3. Multimodal Learning

4. Speech-Driven Animation

- Create and train models on internal databases and proprietary studiodata, leveraging large-scale, high-quality datasets across CGI and VFX pipelines. Implement solutions for :

1. Natural Language Processing (NLP) for automated shot and asset tagging, pipeline task generation.

2. Computer Vision for object tracking, segmentation, and matchmove support. Audio Synthesis and speech-driven animation for automated lip-sync and performance capture. Develop AI-powered stylized content creation workflows, including:

3. Dynamic scene and environment generation. AI-assisted lookdev and texture upscaling. Automated rigging and deformation correction. Crowd simulation and procedural animation enhancements. Lighting and relighting automation for artistic and technical consistency.

4. AI-assisted FX generation (e.g., dust, debris, secondary motion). Automated roto and matte extraction for compositing workflows. Fine-tune pre-trained models (e.g., Hugging Face Transformers, Stable Diffusion, ControlNet) for domain-specific tasks in animation and VFX.

- Leverage TensorFlow, PyTorch, and industry-standard tools for rapid prototyping and scalable, production-ready deployment. Integrate MLOps practices to manage model lifecycle :

1. Data ingestion and preprocessing.

2. Training, validation, and testing pipelines.

3. Deployment in production environments.

5. Monitoring and continuous model evaluation.

- Collaborate with cross-functional teams (Animation, Lighting, FX, Compositing, Pipeline) to translate studio needs into impactful AI solutions.

- Stay updated with the latest advancements in generative AI, CGI, and VFX workflows, integrating cutting-edge research into live projects.

- Conduct performance evaluations to ensure scalability, reliability, and efficiency of AI-assisted pipelines in production environments.

Required Skills and Experience :

- Proficiency in Python and C++ for AI and pipeline integration.

- Hands-on experience with TensorFlow, PyTorch, Hugging Face.

- Experience with generative models :

1. GANs

2. VAEs

3. Transformers

4. Diffusion Models

- Strong understanding of NLP, computer vision, and audio synthesis.

- Experience in training models on large-scale internal/proprietary datasets while maintaining data privacy and quality.

- Familiarity with data preprocessing, augmentation, and feature engineering.

- Exposure to industry-standard CGI and VFX tools (Blender, Maya, Houdini, Nuke, Unreal Engine) for seamless workflow integration.

- Understanding of production pipeline needs in CGI and VFX, including automation opportunities across :

1. Asset creation and retopology

2. Rigging and deformation checks

3. Animation retargeting and clean-up

4. Automated lighting lookdev checks

5. FX simulations leveraging AI

6. Compositing matte generation and cleanup

7. Shot/asset metadata generation for Editorial

- Excellent problem-solving skills with the ability to work independently and collaboratively in a fast-paced production environment.

Preferred Qualifications :

- Advanced degree in Computer Science, Artificial Intelligence, or related fields.

- Published work or contributions to open-source AI/ML projects.

- Experience with generative AI in Animation, Game Development, or VFX pipelines.

- Familiarity with AI-assisted content creation for real-time and offline rendering pipelines.

- Strong mathematical foundation in linear algebra, statistics, and optimization.