Machine Learning Engineer – Video Diffusion Models

Lit8 develops generative AI systems for real-time video generation and enhancement. In this role, you will develop, train, optimize, and deploy advanced video generative models, with a focus on video diffusion models, temporal consistency, motion quality, controllability, and production-ready performance.

We are looking for someone with strong hands-on experience in machine learning and generative AI — especially someone who has trained and improved diffusion models in practice, including video diffusion systems.

Minimum Qualifications

Lit8 develops generative AI systems for real-time video generation and enhancement. In this role, you will develop, train, optimize, and deploy advanced video generative models, with a focus on video diffusion models, temporal consistency, motion quality, controllability, and production-ready performance.

We are looking for someone with strong hands-on experience in machine learning and generative AI — especially someone who has trained and improved diffusion models in practice, including video diffusion systems.

• At least 4 years of hands-on experience in machine learning or deep learning.
• At least 3 years of hands-on experience working with diffusion models, including training, fine-tuning, evaluating, or optimizing them.
• At least 2 years of hands-on experience working with video diffusion models or closely related video generative models.
• Strong experience with video generation, image-to-video, text-to-video, video-to-video, frame prediction, video enhancement, or related visual generation systems.
• Strong understanding of temporal consistency, motion quality, identity preservation, artifacts, flicker, and long-range video coherence.
• Experience with diffusion training and sampling, conditioning, guidance, latent-space generation, and generative model evaluation.
• Strong Python programming skills and hands-on experience with PyTorch or similar frameworks.
• Understanding of video quality evaluation, including perceptual quality, motion stability, artifacts, temporal consistency, FVD, LPIPS, SSIM, or similar metrics.
• Strong problem-solving, analytical, and communication skills.

Preferred Qualifications

• Experience with autoregressive video models, video transformers, or hybrid AR/diffusion approaches.
• Experience with GAN-based video or image generation models.
• Experience with large-scale video model training, distributed training, mixed precision, scalable data pipelines, and dataset curation.
• Experience with controllable video generation, video editing, interpolation, super-resolution, enhancement, or image-to-video workflows.
• Experience optimizing video generation models for real-time, low-latency, or production inference.
• Experience with model optimization techniques such as distillation, quantization, pruning, graph optimization, operator fusion, or hardware-aware tuning.
• Contributions to open-source ML, computer vision, video generation, or generative AI projects are a plus.

Key Responsibilities

Develop, train, and optimize video diffusion models for production use.

Improve video quality, temporal consistency, motion realism, controllability, and robustness.

Work on text-to-video, image-to-video, video-to-video, enhancement, interpolation, and related video generation workflows.

Debug and improve training pipelines, datasets, sampling strategies, and evaluation workflows.

Benchmark models across visual quality, motion quality, artifacts, latency, memory usage, and stability.

Collaborate with research, engineering, and product teams to integrate video generation models into production applications.

What We Offer

• The opportunity to work on advanced video generative AI systems with real product impact.
• A fast-moving, research-driven environment focused on technical excellence and ownership.
• Attractive salary.
• If you are passionate about video diffusion models, temporal generative modeling, and production-grade video AI systems, we’d love to hear from you.