Machine Learning Engineer – AMD Device Deployment for Real-Time 2D Image Generative AI

Lit8 develops generative AI systems for real-time 2D image generation and enhancement on AMD devices. In this role, you will optimize and deploy high-performance image generative AI models, with a focus on low-latency inference, model efficiency, and production-ready performance across AMD hardware platforms.

You will work closely with engineering, product, and platform teams to bring advanced image generation models into real-world applications, ensuring they run efficiently, reliably, and at scale.

Minimum Qualifications

• Ph.D. in Computer Science, Mathematics, Electrical Engineering, or a related field;
• Master’s degree with 2+ years of relevant industry experience;
• Bachelor’s degree with 4+ years of relevant industry experience.

• 2+ years of hands‑on experience optimizing and deploying machine learning models on AMD devices or AMD‑compatible hardware/software stacks.
• Strong expertise in machine learning, deep learning, neural networks, and generative AI models.
• Hands‑on experience with modern ML frameworks such as PyTorch, TensorFlow, JAX, or ONNX‑based workflows.
• Advanced programming skills in Python.
• Solid understanding of model training, evaluation, optimization, and deployment.
• Experience improving inference performance, memory efficiency, and latency.
• Strong problem‑solving, analytical, and communication skills.
• Ability to work effectively in a fast‑paced, multidisciplinary technical environment.

Preferred Qualifications

• Experience with 2D image generative AI, including text‑to‑image, image‑to‑image, inpainting, outpainting, super‑resolution, denoising, image editing, style transfer, or real‑time image enhancement.
• Experience optimizing models through quantization, pruning, distillation, mixed precision, graph optimization, operator fusion, memory optimization, or custom kernels.
• GPU programming or performance tuning experience using HIP, Triton, Vulkan compute, OpenCL, or similar technologies.
• Experience integrating ML models into production applications, device‑specific pipelines, or consumer‑facing products.
• Contributions to open‑source ML, computer vision, image generation, or systems projects are a plus.

Key Responsibilities

• Develop, optimize, and deploy real‑time 2D image generative AI models for AMD devices.
• Build efficient inference pipelines for production use across AMD hardware targets.
• Convert, profile, and optimize models using ONNX, ROCm, HIP, MIGraphX, DirectML, Vulkan compute, or related technologies.
• Improve model performance through quantization, mixed precision, graph optimization, operator fusion, memory optimization, and hardware‑aware tuning.
• Optimize image generation and enhancement models for speed, quality, responsiveness, and reliability.
• Benchmark performance across AMD device configurations, measuring latency, throughput, memory usage, image quality, and stability.
• Collaborate with engineering, product, and platform teams to integrate AI models into production applications.
• Stay current with advances in generative AI, 2D image models, model optimization, and AMD deployment technologies.
• Work cross‑functionally to ensure technical solutions align with product and business goals.

What We Offer

• The opportunity to work at the intersection of real‑time 2D image generative AI and AMD device deployment.
• A fast‑moving, research‑driven environment with real product impact.
• The chance to optimize and deploy next‑generation image generation models on modern AMD devices.
• A culture that values technical excellence, ownership, creativity, and performance engineering.

If you are passionate about generative AI, image generation, model optimization, and high‑performance deployment on AMD platforms, we’d love to hear from you.

#J-18808-Ljbffr…