🛠 Tech Stack

💼 About This Role

You'll design and optimize the core native runtime for LM Studio, working across LLM engines and GPU backends. You'll implement system-level code for concurrency, memory, and IPC, and integrate platform acceleration paths like Metal and CUDA. This role offers the chance to shape the future of on-device AI software.

🎯 What You'll Do

• Contribute to the C++ runtime powering LM Studio
• Extend LLM engine integrations for desktop OS
• Implement resilient IPC and scheduling logic
• Improve build, packaging, and release infrastructure

📋 Requirements

• 4+ years building production C++ systems software
• Deep knowledge of concurrency and memory management
• C++11 (or newer) expertise with RAII mindset
• Experience optimizing performance with profilers

✨ Nice to Have

• Experience with GPU backends (Metal, CUDA, Vulkan)
• Familiarity with llama.cpp or MLX
• Cross-platform development (macOS, Windows, Linux)

🎁 Benefits & Perks

• 💰 Competitive salary with equity
• 🏙️ New York City based, in-person collaboration
• 🧑‍💻 Small team with direct impact
• 🚀 Cutting-edge AI products

📨 Hiring Process

Estimated timeline: 2-3 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· half day