Inference Systems Engineer - Scale & GPU Fleet

Lumaai; Greater London; Hybrid; GBP 100,000 - 140,000; Full time

Job summary

Luma is seeking a systems engineer to own large-scale model serving, integrating new architectures into the inference engine, and scaling deployments across thousands of machines.

You will work with Kubernetes, Linux, Docker, and modern ML stacks to optimize throughput, reliability, and GPU utilization while meeting SLOs across diverse hardware providers, and contribute to the CI/CD of model checkpoints and SDKs.

Qualifications

• Strong Python and system-architecture skills.
• Experience deploying models with PyTorch, Hugging Face, vLLM, SGLang, TensorRT-LLM, or similar.
• Experience with queues, scheduling, traffic control, and fleet management at scale.
• Experience with Linux, Docker, and Kubernetes, and with orchestration, deployment, and scheduling.
• Familiarity with Redis and S3-compatible storage.
• Nice to Have: RDMA networking, 100+ GPU ML systems, CUDA, FFmpeg or multimedia processing.

Responsibilities

• Ship new model architectures by integrating them into the inference engine.
• Collaborate across research, engineering, and infrastructure to optimize model efficiency and deployments.
• Build internal tooling to measure, profile, and track the lifetime of inference jobs and workflows.
• Automate, test, and maintain inference services for maximum uptime and reliability.
• Manage and optimize inference workloads across clusters and hardware providers, and scale deployments across thousands of machines.
• Build scheduling systems that use expensive GPU resources optimally while meeting SLOs, and maintain CI/CD for model checkpoints and SDKs.

Skills

Python

System architecture

Tools

Kubernetes

Docker

Linux

Redis

S3-compatible storage

PyTorch

Hugging Face

vLLM

TensorRT-LLM

Job description

Luma is seeking a systems engineer to own large-scale model serving, integrating new architectures into the inference engine, and scaling deployments across thousands of machines.

You will work with Kubernetes, Linux, Docker, and modern ML stacks to optimize throughput, reliability, and GPU utilization while meeting SLOs across diverse hardware providers, and contribute to the CI/CD of model checkpoints and SDKs.