Distributed ML Infrastructure Engineer for Large-Scale Models

Lumaai; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

Luma seeks an engineer to build distributed systems for training large-scale multimodal models across thousands of GPUs, enabling researchers to focus on innovation atop reliable, efficient infrastructure.

You will tackle PyTorch, CUDA, and distributed training challenges, implementing advanced parallelism (FSDP, Tensor Parallel, Pipeline, Expert Parallel) and developing monitoring/tools to keep runs scalable and stable.

Qualifications

• Extensive distributed PyTorch training on foundation-models.
• Experience with GPU clusters, networking, and storage systems.
• Familiarity with NCCL and MPI for distributed communication.

Responsibilities

• Design, implement, and optimize distributed training systems for models across thousands of GPUs.
• Research and implement advanced parallelization (FSDP, Tensor Parallel, Pipeline Parallel, Expert Parallel).
• Build monitoring, visualization, and debugging tools for large-scale training runs.
• Optimize training stability and resource utilization across massive clusters.

Skills

Distributed PyTorch training

GPU clusters

NCCL/MPI communications

Tools

Containerization

Orchestration

Cloud infrastructure

Job description

Luma seeks an engineer to build distributed systems for training large-scale multimodal models across thousands of GPUs, enabling researchers to focus on innovation atop reliable, efficient infrastructure.

You will tackle PyTorch, CUDA, and distributed training challenges, implementing advanced parallelism (FSDP, Tensor Parallel, Pipeline, Expert Parallel) and developing monitoring/tools to keep runs scalable and stable.