Research Engineer - Agentic Video Editing

We are building the next generation of AI-native creation tools powered by intelligent AI agents. Our mission is to transform how people create by embedding agentic AI directly into creative workflows, from AI-powered camera effect generation to AI-driven video editing and storytelling. Our team operates at the intersection of AI research, systems engineering, and creative product development, translating advances in agentic AI into scalable, real-world creation tools used by millions of creators. We work closely with product and design partners to ensure that sophisticated AI systems result in simple, powerful, and intuitive creative experiences. ## Responsibilities - Build end-to-end agentic video editing systems, working across the agent harness, backend services, and evaluation pipelines. Own scoped features and improvements from prototyping through production. - Develop and improve the agent harness, including planning, tool use, context management, and error recovery for multimodal editing workflows. - Build reliable backend services for agent execution, session management, and media processing, and improve system latency, cost, and reliability. - Develop evaluation and feedback loops, including LLM judges, benchmarks, and human review workflows, to measure editing quality, diagnose failures, and catch regressions. - Propose new ideas and adapt advances from research and industry into practical experiments, using evaluation results and user feedback to continuously improve agent capabilities and video quality. - Collaborate with research, engineering, and product partners to turn successful experiments into useful editing experiences for creators. ## Minimum Qualifications - Bachelor's or Master's degree in Computer Science, AI, or a related field, or equivalent practical experience. - Strong programming skills in Python and solid software engineering fundamentals. - Foundational knowledge of machine learning and large language models. - Hands-on experience building an LLM application, AI Agent, or multimodal AI project through coursework, research, internships, or personal projects. - Ability to design experiments, analyze failures, and turn findings into working improvements. - Interest in video creation and building useful tools for creators. ## Preferred Qualifications - Experience with tool-use agents, context management, or debugging and improving multi-step agent workflows. - Familiarity with video understanding, audio and visual processing. - Experience with evaluation datasets, human annotation, or model-based evaluation. - Familiarity with video editing tools or media processing libraries such as FFmpeg. - Relevant research, open-source contributions, or projects that demonstrate the ability to build and evaluate AI systems.