Mirage
Research Engineer, Agentic Systems
About this role
Mirage is hiring a Research Engineer to develop agentic systems that use large language models for video editing and creative tasks. You'll design end-to-end agent architectures, advance LLM capabilities for multimodal reasoning, and evaluate agent performance on real-world video workflows.
What you'll do
- Design and build end-to-end agentic systems for creative video tasks
- Develop novel training and adaptation approaches for LLMs powering agents
- Create objectives, datasets, and fine-tuning strategies to improve agent behavior
- Explore multimodal reasoning and structured generation for creative control
- Run systematic experiments to evaluate and improve agent performance
- Design evaluation frameworks and analyze failure modes across agent loops
What they're looking for
- Large language models and transformer architectures
- Fine-tuning, alignment, and post-training methods
- Agentic systems and tool use design
- Multimodal reasoning and structured generation
- Production ML systems and full-stack ownership
- Experimental design and evaluation frameworks
- Video analysis and understanding
- Python and ML frameworks
Benefits
- Medical, dental, and vision insurance
- 401(k) with employer match
- Catered lunch multiple days per week
- Dinner stipend for late nights and Grubhub subscription
- Multiple team offsites and monthly team events
- Generous PTO policy
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
- Describe a complex agentic system you've built—what were the key challenges in getting agents to reliably execute multi-step plans?
- Walk us through your approach to designing evaluation metrics for agent behavior. How do you measure success beyond task completion?