Research Engineer (Agentic Systems)

Join Mirage as a Research Engineer specializing in Agentic Systems. In this role, you will push the boundaries of large language models for multimodal creative tasks, focusing on advancing agent capabilities, improving reasoning and control, and enabling new forms of interaction between language models and time-based media. You will design and build end-to-end agentic systems, develop novel training approaches, and run systematic experiments to evaluate and improve agent performance.

• Design and build end-to-end agentic systems for creative tasks, focusing on multimodal reasoning and structured generation.
• Develop novel approaches for training and adapting large language models, including new objectives, datasets, and fine-tuning strategies.
• Run systematic experiments to evaluate and improve agent performance in real-world tasks, and design evaluation frameworks for agentic workflows.

• Experience with fine-tuning, alignment, or post-training methods, especially for adapting models to generate structured outputs or drive tool use
• Comfort owning the full stack, from model-level experiments to deployed agent systems
• Strong experimental rigor and good taste for what makes agents actually work in practice
• Strong track record building production ML systems or agentic pipelines
• Deep understanding of transformers and modern LLM techniques
• BS/MS/PhD in CS, ML, or related field