Senior Machine Learning Engineer - (GenAI)

View full description

Requirements:

• Proven experience deploying diffusion-based models (e.g. latent diffusion, LoRA, ControlNet) into production environments, ideally across dozens or hundreds of GPUs.
• Proficiency in Python and PyTorch, with a focus on optimised inference, model tuning, and memory-efficient execution.
• Familiarity with model deployment tools and practices (e.g. model registries, workflow orchestration, CI/CD for ML).
• Comfort with performance trade-offs, debugging large-scale systems, and delivering improvements fast.
• Experience working in fast-moving, cross-functional teams shipping real-world AI products.
• Ability to pivot quickly between deep technical work, product needs, and cross-functional alignment.

Responsibilities:

• Build and maintain robust production pipelines that deploy generative models across multiple services, each with 100s of GPUs
• Contribute to one of the world’s highest-throughput GenAI systems, generating millions of images and videos daily.
• Utilise quantisation, compilation, caching, distillation, and multi-GPU parallelism to enhance throughput, latency, and stability.
• Collaborate closely with researchers to productionise new capabilities, such as LoRAs, ControlNets, and custom architectures.
• Tackle a wide range of problems — from orchestrating massive multi-GPU video pipelines to optimising end-to-end latency and hardening scalable workloads to run at global scale.