Description:

We are looking for an AI Engineer with expertise in generative AI, specifically in LipSync and FaceSwap technologies.
The ideal candidate will excel in working with diffusion models, video-focused AI solutions, and deploying models in production environments.
Key responsibilities include developing and optimizing workflows for LipSync and FaceSwapping using proprietary and open-source tools.
The engineer will work with diffusion models such as Flux dev and Flux schnell.
They will design their own APIs and utilize others for seamless integration of AI solutions.
Knowledge of prompt engineering techniques for LLMs, image, and video generation tools is required.
The role involves deploying generative AI solutions using Docker, containerization, and cloud platforms like AWS and Google Cloud.
The engineer will leverage platforms such as Replicate and Runpod for efficient deployment and scaling of AI solutions.

Requirements:

Strong proficiency in Python and libraries like PyTorch, Diffusers, Accelerate, TensorFlow, OpenCV, and Pillow is required.
In-depth knowledge of LipSync and FaceSwap solutions, including proprietary and open-source frameworks, is necessary.
Solid experience with API integrations and video AI tools is essential.
The candidate must have the ability to design and train their own models from scratch, including data preparation.
Familiarity with containerization technologies and deploying solutions in Docker is required.
A strong understanding of cloud platforms such as AWS and Google Cloud is necessary.
Proven experience and results in face swapping and lip syncing technologies are required.
Expertise in training and customizing diffusion models and video AI pipelines is essential.
The candidate must be willing to work in a fast-paced environment.