---
title: 'Software Engineer, Agent Harness at LM Studio'
canonical: 'https://feeny.ai/job/software-engineer-agent-harness-lm-studio-new-york-fjvw9gwp8djy'
type: 'job'
last_seen: '2026-09-10'
---

# Software Engineer, Agent Harness at LM Studio

- **Company:** LM Studio
- **Location:** New York, NY
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-08-07
- **Last confirmed live:** 2026-09-10
- **Apply:** https://jobs.ashbyhq.com/lm-studio/87a31fb9-6c5e-4f8a-b226-f3adb44ec7c7

## Job description

LM Studio is used by millions of people around the world to run AI on their own computers, and now with Bionic - also in the cloud. Our values prioritize putting the human in the center, and creating tools that we want to use ourselves, and recommend to our friends and family. As a team, we work with high technical intensity and personal responsibility. We are looking for curious, self-motivated, creative, and technically excellent teammates to join us and build the future of human-AI interactions in software.

## The Role

We are looking for an Agent Harness Software Engineer to build the core agent system behind Bionic, LM Studio’s agent for work and code. You will make open models effective at working with codebases, documents, files, software tools, and the user’s computer. Open models vary widely in how they reason, call tools, use context, and recover from mistakes. You will build the software that handles those differences and gets the best possible agentic performance from models running locally, on linked devices, and in LM Studio's inference cloud.

## Qualifications

- Significant experience building production software involving language models, developer tools, or automation
- Strong understanding of tool calling, structured model output, context construction, and streaming inference
- Experience building stateful systems that perform multi-step work and recover cleanly from failures
- Excellent TypeScript and general software engineering fundamentals
- Deep interest in open models and a practical understanding of their strengths and limitations
- Works with high technical intensity and takes personal responsibility for the finished product

## Responsibilities

- Build and improve the agent harness that powers Bionic
- Make local and cloud models reliable at using files, search, Git, the shell, web tools, and document tools
- Integrate new open models and optimize how they perform in the Bionic agent harness
- Manage conversation history, working context, tool results, interruptions, and recovery
- Build repeatable evaluations and diagnostics for understanding where and why an agent fails
- Constrain the model in a smart way so it remains useful
- Work across Bionic, the LM Studio runtime, and LM Studio cloud to improve the complete system

## Benefits

- Competitive salary and 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 NYC

## About LM Studio

## Company Overview
- **One-liner**: LM Studio provides a local AI toolkit that enables users to discover, download, and run open-source large language models (LLMs) on their own hardware, entirely offline.
- **Entity Type**: Private (Venture-backed, Unattributed VC)
- **Headquarters**: Brooklyn, New York, United States
- **Founded**: 2023
- **Founders**: Yagil Burowski

## Core Business
- **Primary industry**: Artificial Intelligence / Developer Tools
- **Target customers**: B2B and B2C; individual developers, data scientists, and enterprises seeking private, local AI inference.
- **Mission or purpose statement**: To make local AI models more accessible and allow users to run LLMs on their own hardware, privately and for free.

## Products & Services
- **LM Studio Desktop App**: The core product, a free desktop application for macOS, Windows, and Linux that allows users to discover, download, and run open-source LLMs locally. Features include chatting with documents, a built-in API server, and support for agentic tool calling. [lmstudio.ai](https://lmstudio.ai/)
- **LM Studio Enterprise**: A paid offering for organizations that need to deploy local AI at scale, with additional management and security features. [lmstudio.ai](https://lmstudio.ai/enterprise)
- **LM Link**: A service launched in partnership with Tailscale that allows users to access their local models remotely from anywhere, with end-to-end encryption. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
- **SDKs & CLI**: Developer tools including `lmstudio-js` (JavaScript SDK), `lmstudio-python` (Python SDK), and `lms` (CLI) for integrating LM Studio into applications and workflows. [lmstudio.ai](https://lmstudio.ai/)
- **llmster (Headless Deployment)**: A no-GUI version of LM Studio's core for deploying on servers, cloud instances, or in CI/CD pipelines. [lmstudio.ai](https://lmstudio.ai/)

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed.
- **Key Metric**: Total funding of **$19.32M** raised as of a venture round in June 2025. [cbinsights.com](https://www.cbinsights.com/company/lm-studio)
- **Notable Investors/Partners**: FirstMark Capital, Matrix Partners, Torch Capital, Preston-Werner Ventures. [cbinsights.com](https://www.cbinsights.com/company/lm-studio)
- **Growth Signals**: The company has grown headcount by **+100% YoY** to 12 employees. Website traffic has grown **+187.9% yearly**. The company has formed key partnerships with Tailscale (for LM Link) and was featured in Apple's M5 announcement. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)

## Competitive Advantages
- **Privacy-First Local Inference**: Unlike cloud-based AI services, LM Studio runs entirely on the user's hardware, ensuring data never leaves the machine. This is a critical differentiator for privacy-conscious enterprises and developers.
- **Broad Model Support**: Supports a wide range of open-source model formats (GGUF, MLX) and architectures, making it a versatile hub for the open-source LLM ecosystem.
- **Cross-Platform & Apple Silicon Optimization**: Deeply optimized for Apple Silicon (MLX) and NVIDIA GPUs (CUDA), providing strong performance on consumer hardware. The company was featured in Apple's M5 announcement. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
- **Developer-First Ecosystem**: Offers a comprehensive suite of developer tools (SDKs, CLI, REST API) and supports industry standards like OpenAI's API format, making it easy to integrate into existing workflows.

## Strategic Focus
- **Headless & Enterprise Expansion**: The launch of `llmster` (headless deployment) and the Enterprise tier signals a push beyond individual developers into server and enterprise markets. [lmstudio.ai](https://lmstudio.ai/)
- **Remote Access & Networking**: The LM Link partnership with Tailscale aims to make local models accessible from anywhere, bridging the gap between local privacy and remote convenience. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
- **Ecosystem & Partnerships**: Deepening integrations with major AI players (Google DeepMind, NVIDIA, OpenAI) and hardware partners (Apple, NVIDIA DGX) to remain the go-to local inference platform. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)

## Why Work Here
- **High-Impact, Small Team**: With only 12 employees, new hires will have significant ownership and influence over the product and direction. The team is growing rapidly (+100% YoY). [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
- **Cutting-Edge AI Work**: The engineering team works directly on the frontier of local AI, contributing to open-source projects like `llama.cpp`, `mlx-lm`, and `mlx-engine`. [lmstudio.ai](https://www.lmstudio.ai/careers)
- **Global & Remote-Friendly**: While headquartered in Brooklyn, NY, the company has team members in Uruguay and Turkey, suggesting a remote or hybrid-friendly culture. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
- **Open Source Culture**: The company actively contributes to and builds on open-source AI infrastructure, making it an attractive place for engineers who value transparency and community.
- **Current Open Roles**: As of the latest data, LM Studio is hiring for a **Frontend Software Engineer** and a **Systems Engineer (C++)**, indicating a focus on both the user-facing app and the core AI runtime. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)

## Sources
1. [lmstudio.ai](https://lmstudio.ai/)
2. [lmstudio.ai/careers](https://www.lmstudio.ai/careers)
3. [cbinsights.com](https://www.cbinsights.com/company/lm-studio)
4. [linkedin.com](https://www.linkedin.com/company/lmstudio-ai)
5. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/lm-studio)

## Other roles at LM Studio

- [Full Stack Software Engineer](https://feeny.ai/job/full-stack-software-engineer-lm-studio-new-york-hswhkeskpnen) — New York, NY
- [Software Engineer, Inference Runtime](https://feeny.ai/job/software-engineer-inference-runtime-lm-studio-new-york-4sp2mefb88j5) — New York, NY
- [GTM, Enterprise](https://feeny.ai/job/gtm-enterprise-lm-studio-new-york-g4p593zmzqbq) — New York, NY
- [Software Engineer, Application](https://feeny.ai/job/software-engineer-application-lm-studio-new-york-nsj36x3yeen1) — New York, NY
- [Software Engineer, Agent Harness](https://feeny.ai/job/software-engineer-agent-harness-sim-san-francisco-9bex8gkxhwd6) — San Francisco, CA
- [Software Engineer, Agent Harness](https://feeny.ai/job/software-engineer-agent-harness-cartesia-san-francisco-zwydc6cqy9vc) — San Francisco, CA
- [Software Engineer, Agent Harness](https://feeny.ai/job/software-engineer-agent-harness-cursor-san-francisco-5s4q05cj7vqe) — San Francisco, CA
- [Software Engineer, Agent Harness](https://feeny.ai/job/software-engineer-agent-harness-letta-san-francisco-ehs6dm4hvxxh) — San Francisco, CA