About this role
Remote within the EU, Luma AI seeks a Software Engineer for Inference to manage and scale large model serving infrastructure across thousands of machines. This full-time position suits an experienced systems engineer who prefers infrastructure and deployment over pure machine learning modeling.
Role Overview
This position focuses on large-scale inference systems engineering, including scheduling, fleet management, deployment pipelines, and operational reliability. The professional will direct how models are served by integrating new architectures and maximizing GPU resource efficiency.
Key Responsibilities
Requirements
Nice to Have
Skills and Tools
About the Company
Luma AI focuses on developing unified general intelligence capable of generating, understanding, and operating within the physical world. The organization emphasizes multimodality and vision as the next evolution beyond standard language models. Luma AI operates as an equal opportunity employer.
How to Apply
Interested candidates should visit the official Luma AI careers page to submit an application for this remote position.
Skills and tech stack
Questions candidates ask
Where is the Software Engineer, Inference position located?
The job is remote with a location requirement of the European Union (EU).
Does this role involve pure machine learning modeling?
No, this role is firmly on the systems side, focusing on inference infrastructure, model serving, and scaling, rather than pure modeling.
What specific framework and deployment experience is required?
Candidates need experience deploying models with tools such as PyTorch, Hugging Face, vLLM, SGLang, TensorRT-LLM, or similar technologies.
What infrastructure and container tools are needed?
The role requires familiarity with Linux, Docker, Kubernetes, orchestration, deployment, and scheduling.
What is the primary mission of Luma AI?
Luma AI aims to build unified general intelligence that can generate, understand, and operate in the physical world, prioritizing multimodality and vision.