Mirage
Research Engineer, Agentic Systems
Union Square, New York City. Posted a month ago
The role
You will develop new approaches for building and extending agentic systems that understand and operate over complex, real-world video data. The role focuses on advancing agent capabilities, improving reasoning and control, and enabling interaction between language models and time-based media.
What you will do
- Design and build end-to-end agentic systems for creative tasks
- Develop novel approaches for training and adapting the large language models that power these agents
- Design new objectives, datasets, and fine-tuning strategies to improve agent behavior and reliability
- Explore multimodal reasoning and structured generation for creative control
- Run systematic experiments to evaluate and improve agent performance in real-world tasks
- Design evaluation frameworks for agentic workflows in video analysis and editing
- Analyze failure modes across the full agent loop and iterate on improvements
Required qualifications
- BS/MS/PhD in CS, ML, or related field
- Strong track record building production ML systems or agentic pipelines
- Deep understanding of transformers and modern LLM techniques
- 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
Benefits
- Comprehensive medical, dental, and vision plans
- 401K with employer match
- Commuter Benefits
- Catered lunch multiple days per week
- Dinner stipend every night if you're working late and want a bite!
- Grubhub subscription
- Health & Wellness Perks
- Multiple team offsites per year with team events every month
- Generous PTO policy
About the company
Mirage is an AI video company focused on making creation dramatically easier. The team builds multimodal agents, rendering engines, and generative video models for their creative workspace, Captions.