Latest AI JobsBrowse Jobs
Luma AI logo

Research Scientist / Engineer – Reinforcement Learning

Luma AIRedwood City, CAResearch & AI
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Posted
24 Jul 2026
Status
Open · checked 7d ago

About this role

Role Overview

Luma AI is hiring a full-time Research Scientist or Engineer for Reinforcement Learning to build the large-scale systems that make reinforcement learning operational. This position is located in Redwood City, California, with remote flexibility available for qualified candidates.

The role suits professionals who have experience post-training large language models with reinforcement learning and managing asynchronous rollout pipelines at scale.

Key Responsibilities

Design, build, and scale distributed reinforcement learning post-training systems across thousands of GPUs.
Construct high-throughput rollout generation procedures by integrating inference engines, weight synchronization, and asynchronous schemes.
Develop reinforcement learning environments for agentic, multi-step tasks including sandboxed code execution, tool use, and multimodal interaction.
Establish reward infrastructure such as programmatic rewards, reward-model serving, and LLM-as-judge pipelines.
Create evaluation, monitoring, and debugging tools to maintain stability during large training runs.
Collaborate with researchers to advance training efficiency and translate post-training ideas into production.

Requirements

Practical experience in post-training large language models using reinforcement learning methods at a meaningful scale.
Broad background in distributed PyTorch training and model parallelism approaches for foundation models.
Background designing reinforcement learning environments, reward functions, verifiers, or evaluation harnesses for language model agents.
Familiarity with reinforcement learning post-training frameworks and rollout inference engines.
Knowledge of GPU clusters, networking, and communication libraries operating under mixed training and inference workloads.

Nice to Have

Practical background running reinforcement learning training across more than 100 GPUs.
Experience with containerization and orchestration tools like Kubernetes and Ray for large environment fleets.
Documented research contributions in reinforcement learning for language models or open-source contributions to training frameworks.

Skills and Tools

PyTorch
Kubernetes
LLM
vLLM
SGLang
Ray

About the Company

Luma AI aims to construct unified general intelligence capable of generating, understanding, and operating within the physical world. The organization prioritizes multimodality, believing that vision represents the necessary progression beyond language models. Luma AI operates as an equal opportunity employer.

How to Apply

Interested candidates should submit their application through the official Luma AI careers page.

Skills and tech stack

PyTorchKubernetesLLM

Questions candidates ask

What is the location for this role?

The position is based in Redwood City, California, with remote options available.

What department does this role belong to?

This position is part of the Research & AI department.

What type of employment is this?

This is a full-time position.

What tools and frameworks are relevant for this job?

Key technologies include PyTorch, Kubernetes, LLMs, vLLM, SGLang, and Ray.

How should I apply for this position?

Candidates can apply directly on the official Luma AI careers website.

Ready to apply?

The application is on the official Luma AI careers page.

Apply on company site