Software Engineer, Agents

Mirage•New York, NY

6d•$175,000 - $300,000

About The Position

Mirage is an AI video company focused on making creation easier through multimodal agents, rendering technology, and generative video models. Its products include Captions, a creative workspace for generating, editing, and designing video, and Tesseract, which gives AI agents native video-editing capabilities. The Software Engineer, Agents will design and build agentic systems for creative short-form video workflows. The role will help develop agents that take creative actions on users’ behalf, reduce friction, accelerate learning, and unlock new creative possibilities. It involves experimenting with emerging models and techniques and bringing them into production. Engineers on the agents team work across product, machine-learning, and systems engineering. They own meaningful problems end-to-end and help define how agents are built and deployed across the product. Although Mirage does not use hierarchical titles or levels internally, it is hiring engineers who have operated at senior or staff-plus scope. Most roles require in-person work at the company’s New York City headquarters in Union Square.

Requirements

At least 5 years of professional industry experience.
A track record of designing and developing machine-learning systems or agentic pipelines in production.
Deep experience with context engineering, including RAG systems, token optimization, and context management at scale.
Experience building evaluation systems and agentic infrastructure, including context gathering, tool selection, and 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.

Nice To Haves

Experience with multi-agent architectures.
Experience fine-tuning LLMs for specific use cases.
Awareness of developments in generative media and agentic AI technology.
A grounded, collaborative approach and willingness to do whatever it takes to help the team win.
Experience as a startup founder or early engineer at a startup.

Responsibilities

Build and ship end-to-end agentic systems that improve creative workflows while balancing quality, performance, and reliability.
Design agent architectures for gathering context, planning, selecting tools, and reliably executing creative tasks at scale.
Integrate state-of-the-art models, combining internal research and external capabilities to power new agent experiences.
Measure and improve agent quality in production using experimentation, evaluation frameworks, and real-world feedback.