Jan is a productivity company. We build a cross-platform, local-first and AI native framework that can be used to build anything. This includes https://jan.ai/ a desktop app that runs AI on your own laptop, 100% offline and privately. We support most popular AI models, and are actively working on a roadmap to allow users to customize and fine-tune these AIs to meet their specific needs.
We are a fully remote, open source company. We target the global market, but operate as a lean, bootstrapped company.
Responsibilities
- Lead inference development efforts
- Contribute towards Cortex.cpp (github), a multi engine C++, Inference Server for developers
- Contribute towards important open source dependencies like llama.cpp, ONNXRuntime, OpenVINO
Architecture and Planning
- Break down ambiguous goals and high level goals into a well architected, technical execution plan.
- Implement cost-effective solutions, innovates with rapid spikes, avoids “penny wise, pound foolish” trade offs.
Requirements
- Proven experience in C++ development.
- Experience with building a C++ application from the ground up
- Solid understanding of gRPC and its applications in web server optimization.
- Experience in high-performance computing, particularly in hardware optimization and embedded systems.
- Minimum of 3 years of professional work experience in a similar role.
- Self-starter, entrepreneurial mindset, and ability to work independently.
Benefits
- We pay an “all-in” pay and you will cover your own insurance/medical from the amount
- 14 days leave (and unlimited sick days)
- Annual equipment budget (once 2 month probation has been completed)
* Please submit only 1 application, as you will be considered across roles. Duplicate submissions will be automatically archived.
About Homebrew:
Homebrew is an AI R&D studio. We work in the broad area of Local AI, Small Language Models and Multi-modality.
We are the creators and lead maintainers of:
- 👋 jan.ai: Personal AI (2 million+ downloads)
- 🤖 cortex.so: Self-hosted AI Platform
- 🍓 Ichigo-llama3: Native speech model