Job Title

Data Scientist (Video & Image Generation) - 3+ Years, immediate joiner, location agnosticRequired / Must-HaveStrong background in Machine Learning, Deep Learning, and Computer VisionHands-on experience with Generative AI models (diffusion, transformer, or latent video models)Proficiency in Python and ML frameworks such as PyTorch or TensorFlowExperience designing and optimizing video and image generation pipelinesFamiliarity with Azure Machine Learning and cloud-based training/inference workflowsExperience with GPU-based training, distributed computing, and model deploymentKnowledge of multimodal data handling (text, image, video, audio)Experience working with models like Sora, Veo, or Gemini (or similar multimodal systems)Understanding of prompt engineering, fine-tuning, and LoRA/adapters for model adaptationProficiency with tools like Docker, Kubernetes, Databricks, MLflow, and GitStrong analytical, problem-solving, and collaboration skillsNice-to-HaveFamiliarity with Java, React, and Spring Boot for integrating AI capabilities into production toolsKnowledge of model evaluation metrics for visual and temporal quality (e.g., FVD, SSIM, CLIPScore)Experience with OpenCV and FFmpeg for video preprocessing and postprocessingAwareness of recent research in video diffusion, temporal consistency, and multimodal generationPrior contributions to open-source AI projects or published research