Teams at LM Studio

The Systems Engineer will design and optimize the C++ runtime and its integrations, focusing on system-level code, performance tuning, and building infrastructure for AI software across multiple platforms.

Develop and optimize inference runtimes for on-device and cloud deployments. Integrate inference engines, bring up new models and modalities, improve latency, throughput, memory, and reliability across CPU and GPU targets, build batching/scheduling/caching/distributed execution capabilities, benchmark and diagnose performance and correctness, and contribute upstream to open-source projects.

Own the full inbound enterprise sales cycle from first contact to demo, proof-of-concept, close, and expansion. Build processes to capture and convert inbound enterprise interest, identify power users, and drive account-wide adoption.