Luma is building unified general intelligence and seeks a hands-on RL engineer to design and scale post-training systems for policy optimization, rollout, and reward loops across thousands of GPUs. You’ll work on environments, verifiers, and evaluation tooling to keep the loop fast, stable, and correct.
You'll bring experience with post-training LLMs, distributed PyTorch, and RL frameworks, and contribute to production systems that run at frontier scale.
#J-18808-Ljbffr
Distributed RL Infrastructure Scientist employer: Luma
At Luma AI, we pride ourselves on being an innovative employer that fosters a dynamic and collaborative work culture. As an Executive Assistant in the UK, you will play a pivotal role in shaping our operational strategies while enjoying opportunities for personal and professional growth in a fast-paced environment. With a commitment to expanding human imagination through cutting-edge technology, we offer a unique chance to make a meaningful impact alongside a passionate team dedicated to transforming the creative landscape.
