About the Role

When people get a model running on their own machine, the next question often is, "Great, now what can I actually do with it?". This is where you come in.

Description

Local, on-device AI has clear advantages: privacy, offline availability, predictable cost, and data control for both home and business users. Your job will be to turn those advantages into concrete features: tool-using assistants, agentic RAG, document understanding, data analysis and manipulation, code assistants of various kinds, and anything else that makes local AI genuinely useful.

The work spans applied research, rapid prototyping, systematic evaluation, and production engineering delivered to a large and enthusiastic user base worldwide.

Responsibilities

• Push the boundaries of what’s possible with local AI by designing and implementing new features
• Identify and scope high-impact local AI use cases (RAG, document understanding, data analysis, code intelligence) and design end-to-end solutions
• Prototype algorithms quickly, run systematic evaluations, and promote successful approaches into LM Studio’s production codebase
• Survey recent papers and open-source work; adapt, implement, and benchmark promising ideas on consumer hardware
• Collaborate with app, systems, and API focused team members to ship reliable features to a rapidly growing user base and iterate based on real-world feedback
• Build automated test and benchmarking harnesses to track accuracy, latency, and memory across model versions and tasks

Minimum Qualifications

• 3+ years writing software every day (TypeScript or Python preferred; C++ a plus) - internships included
• Demonstrated experience shipping LLM-powered features
• Track record of running systematic experiments and using results to make algorithm choices
• Ability to profile and debug performance issues at the model, runtime, or systems level
• Strong written and verbal communication

Preferred Qualifications

• Excellent ability to present your work to both technical and non-technical audiences
• Experience publishing technical blog posts, conference papers, or open-source projects in NLP or IR
• Background in information retrieval, compiler tooling, or systems performance engineering
• History of maintaining SDKs, CLIs, or public APIs

Pay and Benefits

• Equity
• Medical, Dental, Vision insurance
• 401K
• Company-provided MacBook Pro M3 or high-performance Windows/Linux laptop
• Access to a range of hardware (GPUs, servers, devices)
• Office in the Brooklyn Navy Yard with water views and free gym access

Annual Salary Range:
$165,000 – $350,000 USD