Agent Behavior Designer

<h3><strong style="background-color: transparent; color: rgb(67, 67, 67);">About Luma AI</strong></h3><div><span style="background-color: transparent; color: rgb(0, 0, 0);">Luma's mission is to build multimodal AI to expand human imagination and capabilities. We believe that multimodality is critical for intelligence. To go beyond language models and build more aware, capable, and useful systems, the next step function change will come from vision. So, we are working on training and scaling up multimodal foundation models for systems that can see and understand, show and explain, and eventually interact with our world to effect change.</span></div><div><br></div><h3><strong style="background-color: transparent; color: rgb(67, 67, 67);">About the Role</strong></h3><div><span style="background-color: transparent; color: rgb(0, 0, 0);">Luma is pushing the boundaries of generative AI, building tools that redefine how visual content is created. We’re seeking an </span><strong style="background-color: transparent; color: rgb(0, 0, 0);">Agent Behavior Designer</strong><span style="background-color: transparent; color: rgb(0, 0, 0);"> to help shape the logic, personality, and execution of Luma Agents within our core canvas platform.</span></div><div><br></div><div><span style="background-color: transparent; color: rgb(0, 0, 0);">This is an emerging and highly specialized discipline. While this role does not require shipping traditional full-stack production code, it extends far beyond standard prompt engineering. You will operate at the forefront of agentic engineering, working closely with the agent's core behavior, controlling its logic through sophisticated prompting stacks, and tracing causality across complex codebases and execution logs. You will define optimal user experiences, rigorously test agent behavior to identify suboptimal patterns, and iteratively refine complex prompt stacks to resolve them.</span></div><div><br></div><div><span style="background-color: transparent; color: rgb(0, 0, 0);">The ideal candidate demonstrates meticulous attention to linguistic nuance, possesses the technical proficiency to build Python evaluation harnesses, and exhibits the analytical rigor to iteratively resolve complex behavioral challenges.</span></div><div><br></div><h3><span style="background-color: transparent; color: rgb(67, 67, 67);">What You'll Do</span></h3><ul><li class=""><strong style="background-color: transparent;">Diagnose & Debug:</strong><span style="background-color: transparent;"> Analyze complex agent traces and system logs to identify the root causes of suboptimal outputs. Trace causality through non-standardized text and prompts to resolve unexpected agent behaviors.</span></li><li class=""><strong style="background-color: transparent;">Shape Agent Logic:</strong><span style="background-color: transparent;"> Architect and refine prompt stacks to align agent behavior with intended outcomes. Oversee context window management and implement tool-calling best practices to ensure optimal agent functionality.</span></li><li class=""><strong style="background-color: transparent;">Build Evals & Ground Truth:</strong><span style="background-color: transparent;"> Develop Python-based scripts and evaluation harnesses for robust quantitative and qualitative testing. Partner collaboratively with the Evals team to define performance baselines and measurement frameworks.</span></li><li class=""><strong style="background-color: transparent;">Understand and Advocate for the User Experience:</strong><span style="background-color: transparent;"> Leverage a deep understanding of language, tone, and user intent to ensure agent interactions are intuitive, highly responsive, and creatively enabling within a media-generation environment.</span></li></ul><div><br></div><h3><span style="background-color: transparent; color: rgb(67, 67, 67);">Who You Are</span></h3><ul><li class=""><strong style="background-color: transparent;">2-3 Years of Experience:</strong><span style="background-color: transparent;"> Professional experience in a technology-driven environment, with a strong preference for backgrounds that blend analytical and creative problem-solving with deep linguistic or communicative skills.</span></li><li class=""><strong style="background-color: transparent;">Proven AI/Agentic Experience:</strong><span style="background-color: transparent;"> Demonstrated hands-on experience building AI or agentic workflows within the past two years. Candidates without direct industry experience at an AI company must provide a robust portfolio of personal projects or products demonstrating these capabilities.</span></li><li class=""><strong style="background-color: transparent;">Technical Literacy:</strong><span style="background-color: transparent;"> Ability to manage a local development environment, navigate code repositories, write functional Python scripts, and utilize Git/GitHub. (Shipping production-level product code is not required; submitting PR’s, navigating codebase, and resolving errors is).</span></li><li class=""><strong style="background-color: transparent;">Exceptional Command of Language:</strong><span style="background-color: transparent;"> Advanced proficiency in written communication, with an intuitive understanding of how precise linguistic adjustments impact AI model outputs. In this domain, prose functions as code.</span></li><li class=""><strong style="background-color: transparent;">Analytical Persistence & Qualitative Judgment:</strong><span style="background-color: transparent;"> The persistence to iterate continuously through complex edge cases and the qualitative judgment to discern when a creative tool delivers an optimal user experience.</span></li><li class=""><strong style="background-color: transparent;">AI Tool Proficiency:</strong><span style="background-color: transparent;"> Advanced proficiency with AI coding assistants (e.g., Cursor, GitHub Copilot) and related AI productivity tools.</span></li></ul><div><br></div><h3><span style="background-color: transparent; color: rgb(67, 67, 67);">Bonus Points</span></h3><ul><li class=""><span style="background-color: transparent;">Experience building and operating Reinforcement Learning (RL) pipelines.</span></li><li class=""><span style="background-color: transparent;">Diverse hybrid backgrounds (e.g., intersections of humanities-focused study/role and Computer Science, Linguistics, or Data Analysis, or deeply technical self-taught endeavors).</span></li><li class=""><span style="background-color: transparent;">Experience with AI media generation, editing, and manipulation across modalities (video, images, 3D).</span></li><li class=""><span style="background-color: transparent;">Deep familiarity with creative workflows and the foundational tools digital artists use to craft visual narratives.</span></li></ul><div><br></div>

Back to blog

Other Jobs To Apply

No other job posts for this day.