We are looking for a well-rounded AI/ML Systems Engineer to join our team and build LM Studio with us. The ideal candidate loves working at the intersection of machine learning and systems engineering, is a prolific problem solver, and is passionate about building great products.
Specifically, you will build and evolve on-device inference engines and integrations for local LLMs and other AI technologies in LM Studio. In this role you will design and maintain the runtime that powers on-device model inference, ship day-0 support for new models, and optimize performance across a wide range of hardware configurations.
You will work closely with model authors and upstream open-source communities (e.g., llama.cpp, MLX, and more) to ensure LM Studio users have access to the latest and greatest AI experiences.
This role might be for you if you are passionate about living at the boundary between models and systems, and you care deeply about shipping great local AI-powered experiences for both end users and developers.
ResponsibilitiesBuild and maintain world-class on-device inference engines for LLMs and other models.
Integrate emerging AI/ML technologies as production-ready features in LM Studio.
Develop with and contribute to OSS engines like llama.cpp, MLX, and more.
Collaborate closely with model authors to ship day-0 support for new models.
Profile, debug, and improve process memory, CPU usage, and GPU usage.
Be an excellent communicator, contributor, and collaborator.
3+ years of experience with C++ and Python. TypeScript experience is a plus.
2+ years of experience with machine learning frameworks and model inference.
Excellent problem-solving and communication skills.
Strong understanding of operating systems.
Strong understanding of software system design.
Into local LLMs and have tinkered with them in LM Studio.
Passionate about a great user and developer experience.
We aim to build delightful and potent creation tools for AI. We are a small team based in New York. Everyone on the team is IC-minded, intellectually curious, self-motivated, and loves software. We care deeply about our user community and we strive to build canonical software that users and developers love.
Our products include the LM Studio desktop app, our developer SDKs: lmstudio-js and lmstudio-python, our CLI lms, MLX engine mlx-engine for M-chip Macs, venvstacks which enables us to ship Python-based software, the collaboration Hub for individuals and teams, and more currently being built.
