Machine Learning Engineer – Image Super-Resolution

Lit8 develops generative AI systems for real-time image enhancement and super-resolution. In this role, you will develop, optimize, and deploy AI models that improve image quality, resolution, sharpness, and visual detail in real time.

You will work closely with research, engineering, and product teams to build fast, efficient, production-ready super-resolution systems.

Minimum Qualifications

• At least 2 years of hands-on experience with image super-resolution, image enhancement, or image restoration models.
• Strong experience with deep learning for computer vision and image processing.
• Hands-on experience training, fine-tuning, evaluating, and optimizing image enhancement models.
• Experience with super-resolution architectures, including CNN-based, GAN-based, transformer-based, or diffusion-based models.
• Strong Python programming skills.
• Hands-on experience with PyTorch or similar ML frameworks.
• Understanding of image quality evaluation, including perceptual quality, artifacts, sharpness, stability, PSNR, SSIM, LPIPS, or similar metrics.
• Strong problem-solving, analytical, and communication skills.

Preferred Qualifications

• Experience developing real-time super-resolution models for video, gaming, streaming, creative tools, mobile, or edge applications.
• Experience with related image enhancement tasks such as denoising, deblurring, upscaling, artifact removal, or frame enhancement.
• Experience with model optimization techniques such as quantization, pruning, distillation, mixed precision, graph optimization, or operator fusion.
• Experience deploying ML models into production applications or device-specific pipelines.
• Familiarity with inference and deployment frameworks such as ONNX, TensorRT, OpenVINO, Core ML, DirectML, ROCm, Vulkan, or similar technologies.
• Knowledge of GPU performance optimization, custom kernels, or hardware-accelerated image processing.
• Contributions to open-source ML, computer vision, image restoration, or image enhancement projects are a plus.

Key Responsibilities

• Develop and optimize real-time image super-resolution models for production use.
• Train, fine-tune, and evaluate models for upscaling, enhancement, restoration, denoising, deblurring, and artifact reduction.
• Improve model speed, memory efficiency, visual quality, and robustness.
• Optimize inference performance through compression, quantization, distillation, mixed precision, graph optimization, and hardware-aware tuning.
• Benchmark models across latency, throughput, memory usage, perceptual quality, artifacts, and stability.
• Evaluate new architectures for efficient image super-resolution and enhancement.
• Collaborate with research, engineering, and product teams to integrate models into production applications.
• Stay current with advances in super-resolution, image restoration, efficient vision models, and real-time inference.

What We Offer

• The opportunity to work on advanced real-time image super-resolution and enhancement systems.
• A fast-moving, research-driven environment with real product impact.
• A culture that values technical excellence, ownership, creativity, and performance engineering.
• Attractive salary.

If you are passionate about image super-resolution, real-time AI systems, and production-grade model optimization, we’d love to hear from you.