Systems Engineer (C++)

LM STUDIO INC.
New York, NY, United States
2 months ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Experienced
Experience required
4 years minimum
Compensation
$175,000.0 - $275,000.0
Working hours
Regular working hours
Job source

Tech stack

Microsoft Windows Application Programming Interfaces (APIs) Artificial Intelligence Apple Mac Systems Systems Engineering C++ (Programming Language) Profiling Nvidia CUDA Software Debugging Linux File Systems Memory Management
+5 more
Network Protocols Performance Tuning Software Engineering Large Language Models Concurrency

Job description

We are hiring a C++ Systems Software Engineer in New York City. You design, build, and optimize the core native runtime that powers LM Studio and the C++ libraries powering the app and our APIs. You will work across our runtime, LLM engines, llama.cpp/MLX integrations, build infrastructure, and the future of our on-device AI software. Your work centers on system and library integration: wiring our C++ runtime to GPU backends, vendor SDKs, and operating-system services to support user-facing applications. You will implement and harden system-level code (threading, memory, files, IPC, scheduling) and integrate platform acceleration paths (Metal, CUDA, Vulkan) across macOS, Windows, and Linux. You will profile, debug, and tune the execution paths that make local AI fast and dependable, and our software well architected and maintainable., * Contribute to the C++ runtime that powers LM Studio

  • Extend our LLM engine integrations and build platform-aware performance features for desktop operating systems.
  • Implement resilient IPC, resource management, and scheduling logic to support concurrent model execution.
  • Improve our build, packaging, and release infrastructure for native components.
  • Collaborate with the rest of the team to deliver cohesive and recognizable user experiences., We are looking for engineering excellence and strong values / cultural fit. If your application appears to be a good match we’ll reach out to schedule an initial call. If all goes well, we will proceed to 2-3 technical interviews. The final step in the process is an onsite interview in our New York office, where you will work through several more technical sessions focused around system design and architecture, meet the team and see how we work.

Requirements

Do you have experience in System tuning?, * 4+ years building production C++ systems software across macOS or Linux.

  • Thinks in systems and knows how to reason about performance, reliability, and user experience end-to-end.
  • Proven maturity designing internal and external APIs that are ergonomic, maintainable, and stable over time.
  • C++11 (or newer) expertise with RAII as a default mindset and modern language/library proficiency.
  • Deep knowledge of concurrency, memory management, file systems, and network protocols.
  • Experience optimizing performance with profilers, tracing, and hardware counters.

Benefits & conditions

Pulled from the full job description

  • Health insurance
  • Paid time off
  • Vision insurance
  • Dental insurance, * Competitive salary and generous equity grants
  • Great medical, vision, dental healthcare plans
  • Catered team lunch / expensed dinners in the office
  • Flexible PTO
  • Flexible WFH
  • Sun drenched office in SoHo in Manhattan, NY
  • Access to cool powerful hardware of all kinds

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

1:31 min

Profiling computing workloads across environments using Performance Studio

Andrew Wafaa Andrew Wafaa · WWC 2024

52 sec

Running persistent Linux environments directly on Windows

Ben Breard Ben Breard · WWC 2025

47 sec

Profiling native execution calls with async-profiler

Gonzalo Ortiz Jaureguizar Gonzalo Ortiz Jaureguizar · WWC Europe 2026

5:59 min

Analyzing concurrency bottlenecks in standard serverless architectures

Marco Plaul Marco Plaul +1 · WWC 2023

1:55 min

Introduction to systems programming and performance in .NET

Szymon Kulec Szymon Kulec · WWC Europe 2026

3:55 min

Demonstrating .NET installation on Debian and Azure Linux

Silvano Coriani Silvano Coriani · Europe 2026 Virtual

Videos

See all

Related articles

See all