Mirage
Research Engineer, Agentic Systems
About this role
Mirage is hiring a Research Engineer to develop agentic systems that help LLMs understand and edit video through natural language. You'll design end-to-end agent architectures, advance model training techniques, and build evaluation frameworks for creative AI workflows.
What you'll do
- Design and build end-to-end agentic systems for video editing and creative tasks
- Develop novel fine-tuning and adaptation strategies for large language models
- Create datasets, objectives, and training approaches to improve agent behavior and reliability
- Explore multimodal reasoning and structured generation for creative control over video
- Run systematic experiments to evaluate agent performance on real-world creative tasks
- Analyze failure modes across planning, tool use, and execution loops to iterate on improvements
What they're looking for
- Large language models and transformer architectures
- Agentic systems and agent design patterns
- Fine-tuning, alignment, and post-training methods
- Structured output generation and tool use
- Multimodal reasoning (video + language)
- Experimental design and evaluation frameworks
- Production ML systems and full-stack ML ownership
- Video understanding and analysis
Benefits
- Medical, dental, and vision coverage
- 401K with employer match
- Catered lunch multiple days per week and dinner stipends
- Commuter benefits and Grubhub subscription
- Health and wellness perks
- Generous PTO and multiple annual team offsites
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Mirage
Mirage builds an AI-native video platform that leverages generative media and large language models to enable sophisticated video production, editing, and creative workflows. The company is hiring backend engineers, full-stack software engineers, ML engineers, and iOS developers to advance their AI-driven platform and enhance user experiences in web-based and mobile media creation.
View all jobs at MirageLikely interview questions
- Walk us through a complex agentic system you've built—what were the key challenges in getting the agent to reason reliably?
- How have you approached fine-tuning or aligning LLMs for tool use and structured outputs in past projects?