Software Engineer, Agents
Union Square, New York City · 5+ years experience · Full-time · Posted Oct 8, 2026
At a glance
- Experience
- 5+ years experience
- Employment
- Full-time
- Location
- Union Square, New York City
About the role
- This role focuses on designing and building agentic systems that power creative workflows for short-form video. You will help shape how AI agents reduce friction and unlock new creative possibilities by building agents that perform creative actions on a user's behalf.
Responsibilities
- Build and ship end-to-end agentic systems that improve creative workflows, balancing quality, performance, and reliability.
- Design agent architectures, including how agents gather context, plan, select tools, and execute 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.
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, including RAG systems, token optimization, and context management at scale.
- Experience building evaluation systems and agentic infrastructure such as context gathering, tool selection, and multi-step planning.
- Exceptional problem-solving fundamentals and ability to learn quickly.
- Ability to operate effectively in a fast-paced environment and scope/deliver projects end-to-end.
Benefits
- Comprehensive medical, dental, and vision plans
- 401K with employer match
- Commuter Benefits
- Catered lunch multiple days per week
- Dinner stipend for late work
- Grubhub subscription
- Health & Wellness Perks
- Multiple team offsites per year
- Monthly team events
- Generous PTO policy
Skills
- ML Systems
- Agentic Pipelines
- RAG Systems
- Token Optimization
- Context Management
- Evaluation Systems
- Agentic Infrastructure
- LLMs
