AI Engineering Internship
Chert (YC P26) is the infrastructure to build and scale AI agents on the channels people already use. We started by making iMessage programmable at scale, and now we let anyone put a realtime AI video agent on a live FaceTime call with one API.
We're backed by Y Combinator (P26), Z Fellows, Beta Fund, and angels from OpenAI, Anthropic, NVIDIA, Meta, Scale AI, Grafana, and LinkedIn.
What you'll do:
Build realtime AI video agents on FaceTime for use cases traditional text or voice-based agents can't handle. Concretely:
- Build multimodal agents for FaceTime (vision + LLMs + speech + video)
- Deploy and distribute to real customers and users
- Prototype use cases only possible when an agent can continuously see and hear (e.g. realtime gym coaches, study partners, assistants, and more)
You:
A strong builder who can turn an idea into a working prototype fast. You might be a fit if you:
- Are strong with AI coding tools (Codex, Claude Code, Cursor, etc.)
- Have experience with WebRTC, realtime audio/video, LLMs, multimodal models, or AI agents
- Have taste for novel product experiences
- Like ambiguous problems at the edge of what's currently possible
This is a high-ownership role. You'll take ideas from prototype to working demo quickly and help define what people actually use realtime video agents for.