SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mirage (operating under the brand Captions) is an AI video company building multimodal agents and generative video models to make creative work dramatically easier. The company has raised $75M from top-tier investors including Sequoia, Andreessen Horowitz, Kleiner Perkins, and Index Ventures.
You will design and build agentic systems that power creative workflows for short-form video. The role focuses on reducing friction in creative processes, accelerating learning, and unlocking new possibilities for users through AI agents that can take creative actions on their behalf. You'll work across product, machine learning, and systems engineering, owning meaningful problems end-to-end and helping define how agents are built and deployed across the product.
Key responsibilities include:
- Building and shipping end-to-end agentic systems that improve creative workflows while balancing quality, performance, and reliability
- Designing agent architectures: how agents gather context, plan, select tools, and execute creative tasks reliably at scale
- Integrating state-of-the-art models, combining internal research and external capabilities to power new agent experiences
- Measuring and improving agent quality in production through experimentation, evaluation frameworks, and real-world feedback
The company emphasizes that while they don't use hierarchical titles internally, they are currently hiring engineers who have operated at senior or staff+ scope. Most roles require in-person presence at the NYC HQ in Union Square.
REQUIREMENTS:
- 5+ years of professional industry experience
- Track record of designing and developing ML systems or agentic pipelines in production
- Deep experience with context engineering: RAG systems, token optimization, context management at scale
- Experience building evaluation systems and agentic infrastructure (context gathering, tool selection, multi-step planning)
- Exceptional problem-solving fundamentals and ability to learn quickly in a rapidly evolving space
- Ability to operate effectively in an extremely fast-paced environment and scope and deliver projects end-to-end
PREFERRED:
- Experience with multi-agent architectures
- Experience fine-tuning LLMs for specific use cases
- Understanding of where generative media and agentic AI technology is heading
- Grounded, collaborative approach and willingness to do whatever it takes to help the team win
- Background as a startup founder or early engineer at a startup
