Research Engineer

Luma AI is seeking a Research Engineer to enhance our model evaluation processes in the realm of generative AI. Leverage your expertise to build automated evaluation pipelines and improve visual content outcomes.

As a Research Engineer at Luma AI, you will play a pivotal role in assessing the performance of multimodal models. This position combines research and engineering, focusing on the development of systems that evaluate and refine generative models' outputs. You’ll work collaboratively to ensure high-quality evaluations that directly impact model advancements.

Key Responsibilities:

• Implement scalable pipelines for model evaluation
• Create metrics for fidelity and human intent alignment
• Integrate evaluation feedback into models continuously
• Manage testing and monitoring infrastructure
• Partner with teams for automated evaluations

Requirements:

• Master’s or PhD in relevant technical fields
• Over 5 years of experience with ML evaluation
• Hands-on visual data experience required
• Strong skills in Python and ML tools
• Familiarity with automation in evaluation workflows

Drive innovation in AI output assessments at Luma AI as part of a dynamic team.