Software Engineer, Agents
CaptionsUnion Square, New York CityOn-Site
Needs a free Superjobs account. You'll finish on Captions's Ashby page.
Skill score
Summary
This software engineer designs and ships agentic systems that carry out creative video editing tasks for users, covering context gathering, planning, tool selection and evaluation in production. It suits a senior or staff-level engineer with at least five years of industry experience who has built ML or agent pipelines before and works well in a fast-paced startup.
- Function
- Development
- Estimated salary
- Est. $138k–208k/yr
- Estimated for a mid-level role, ~5 yrs experience, United States. Not published by the employer.
- Work mode and location
- On-Site, Union Square, New York City
- Experience
- 5+ yrs
- Employment type
- Full-time
Job description
Overview
This role focuses on designing and building agentic systems that power creative workflows for short-form video. You'll help shape how AI agents reduce friction, accelerate learning, and unlock new creative possibilities for our users — building agents that can take creative actions on a user's behalf — while experimenting with emerging models and techniques to bring these experiences to life in production.
About the team
Software Engineers on the agents team work across product, machine-learning, and systems engineering — owning meaningful problems end-to-end and helping define how our agents are built and deployed across the product.
While we don’t use hierarchical titles or levels internally, we are currently hiring engineers who have operated at senior or staff+ scope.
Roles and responsibilities
- Build and ship end-to-end agentic systems that meaningfully improve creative workflows, balancing quality, performance, and reliability
- Design agent architectures — how agents gather context, plan, select tools, and execute creative tasks reliably 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 to guide iteration
Skills required
Top skills
- Agentic systems
- ML systems in production
- Context engineering
- RAG systems
All skills (6)
- Evaluation frameworks
- Agent architecture design
- Multi-step planning
- Multi-agent architectures
- LLM fine-tuning
- Generative media
Qualifications
- 5+ years of professional industry experience
- A 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
- Able to operate effectively in an extremely fast-paced environment and scope and deliver projects end-to-end
Nice to have
- You have worked with multi-agent architectures
- You have experience fine-tuning LLMs for specific use cases
- You have a pulse on where generative media and agentic AI technology is going
- You are grounded, collaborative, and willing to do whatever it takes to help the team win
- You have been a startup founder or an early engineer at one
Other details
Explore our work
Captions — Our flagship creative workspace
Tesseract — Our professional video engine for AI agents
Research — The foundation models we build in-house
Updates — The latest from Mirage
TechCrunch, Forbes, Fast Company — Press
Please note that most of our roles will require you to be in-person at our NYC HQ (located in Union Square)
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
Company info
About Captions
Captions builds foundation models and products intended to change how videos are made. The sources do not name specific users of its products beyond the broader goal of helping brands grow through video.