
- Founded
- 2025
- Employees
- 3
About Cactus
App developers can now deploy private, local, offline AI models in their mobile apps, achieving up to 150 tokens/sec and <50ms time to first token. Cactus is used by 3k+ developers and completes 500k+ weekly inference tasks on phones today. It is open-source! Check out the repo: https://github.com/cactus-compute/cactus
Open Jobs at Cactus (2)
- AI Research EngineerSan Francisco, CA, US / Remote (San Francisco, CA, US)Mid-Level$120k – $180kPosted Mar 14, 2026
- AI Inference EngineerSan Francisco, CA, US / RemoteMid-Level$120k – $180kPosted Mar 14, 2026