Machine Learning Engineer – GAN-Based Image Generative AI

Lit8 develops generative AI systems for real-time image generation and enhancement . In this role, you will focus on developing, training, and improving GAN-based image generation models , with an emphasis on visual quality, stability, controllability, and production-ready performance.

We are looking for someone with deep hands-on GAN experience — someone who has trained GANs, debugged adversarial training, improved image quality, and worked directly with generator-discriminator systems.

Minimum Qualifications

Lit8 develops generative AI systems for real-time image generation and enhancement . In this role, you will focus on developing, training, and improving GAN-based image generation models , with an emphasis on visual quality, stability, controllability, and production-ready performance.

We are looking for someone with deep hands-on GAN experience — someone who has trained GANs, debugged adversarial training, improved image quality, and worked directly with generator-discriminator systems.

• At least 3 years of hands-on experience working with GANs , including training, fine-tuning, debugging, and optimizing GAN-based image generation models.
• Strong practical experience with generator-discriminator training, adversarial losses, training stability, mode collapse mitigation, and image-quality optimization.
• Experience building or improving image generation, image-to-image, enhancement, super-resolution, inpainting, style transfer, or related visual generation systems.
• Hands-on experience training, evaluating, and debugging generative models at the model, data, and loss-function level.
• Strong experience with deep learning for computer vision and image processing.
• Strong Python programming skills.
• Hands-on experience with PyTorch or similar deep learning frameworks.
• Understanding of image quality evaluation, including perceptual quality, artifacts, sharpness, realism, consistency, FID, LPIPS, SSIM, or similar metrics.
• Strong problem-solving, analytical, and communication skills.

Preferred Qualifications

• Experience with large-scale GAN systems, such as GigaGAN-style architectures , high-resolution GANs, or production-scale image generation models.
• Experience training GANs on large datasets with distributed training, mixed precision, data curation, and scalable experiment workflows.
• Experience distilling diffusion models into GAN-based models .
• Experience optimizing models for low-latency or production inference.
• Experience with model optimization techniques such as quantization, pruning, distillation, graph optimization, operator fusion, or hardware-aware tuning.
• Contributions to open-source ML, computer vision, image generation, or GAN-related projects are a plus.

Key Responsibilities

• Develop, train, and optimize GAN-based image generation models .
• Improve image quality, realism, sharpness, stability, and controllability.
• Debug and improve GAN training pipelines, losses, data workflows, and convergence behavior.
• Evaluate models across visual quality, artifacts, latency, memory usage, and robustness.
• Collaborate with research, engineering, and product teams to integrate GAN-based models into production applications.

What We Offer

• The opportunity to work on advanced GAN-based image generative AI systems with real product impact.
• A fast-moving, research-driven environment focused on technical excellence and ownership.
• Attractive salary.