LM Studio

Build end-to-end features for LM Studio and Bionic across web platforms, APIs, SDKs, and desktop applications. This role suits a technically strong full-stack engineer who enjoys working from user experience through distributed systems and performance.

Build and optimize inference runtimes that power LM Studio’s on-device and cloud AI experiences. You’ll work across new models, multimodal execution, CPU/GPU performance, and open-source inference infrastructure.

Build the agent harness behind Bionic, making open models reliable at working with codebases, documents, files, software tools, and users’ computers. You’ll design stateful, fault-tolerant systems and optimize agent performance across local and cloud inference.

Build and ship LM Studio features used by millions of people, combining UI work, systems engineering, product design, and applied AI or agentic engineering. This in-person New York City role suits an engineer who enjoys crafting software products across the stack.