AI Inference Engineer

Cactus is pioneering the development of a cross-platform open-source framework that enables AI models to run locally on smartphones. As an AI Inference Engineer, you'll be at the forefront of building and maintaining AI SDKs for mobile developers, combining expertise in native mobile development, artificial intelligence, and cross-platform frameworks like React-Native and Flutter.

The role requires a strong technical foundation with a Bachelor's or Master's degree in CS, Engineering, or equivalent experience. You'll need demonstrated expertise in React Native library development and native mobile development (iOS, Android), along with practical experience working with LLMs, AI agents, and machine learning systems.

What makes this role unique is the opportunity to work directly with enterprises, helping them implement and optimize AI solutions on mobile platforms. The position demands a high sense of ownership and agency, perfect for someone who thrives on taking initiative and seeing projects through from conception to deployment.

The company has recently completed a highly oversubscribed fundraising round and is actively scaling its engineering team, making this an exciting time to join. You'll be working with a small but growing team, contributing to an open-source project that's pushing the boundaries of mobile AI implementation.

Benefits include a competitive salary range of $120,000 - $180,000, generous equity based on experience, comprehensive health insurance, gym membership, and the invaluable experience of working at a YC-backed startup. The position offers flexibility with both San Francisco-based and remote options, and includes visa sponsorship for international candidates.