All jobs
Senior/Staff Kotlin Desktop Engineer – AI Inference Tooling
TechTree's client
Salary
PLN 252k – PLN 373k
Work mode
Remote
What we're looking for
- Strong Kotlin skills
- Understanding of asynchronous and concurrent programming with Kotlin Coroutines
- Awareness of cross-platform differences
- Fluency in English
- Self-motivation and ability to take full ownership of features
About the role
About the Role:
- Join a small, startup-like team focused on building a desktop tool for local AI inference.
- Work with Kotlin and Compose Desktop to develop an application that deploys, configures, and manages AI models on local devices.
- Daily tasks include building the UI in Compose Desktop, integrating with backend REST APIs for model deployment, and setting up agent configurations using TOML/JSON/YAML files.
- Involve in LLM proxy routing and creating installers for Windows, macOS, and Linux.
- The team has an internal MVP and is in direct communication with potential users, aiming to make the tool open source.
- Opportunity to shape a developer tool from its early stages.
Project Scope:
- Develop a desktop application for deploying and configuring local inference on devices like NVIDIA Spark/DGX Spark.
- Manage model lifecycle (start/stop) and connect coding agents like Claude Code and Codex to locally hosted models.
- Currently an internal MVP, with plans to open source.
Tech Stack:
- Kotlin, Compose Desktop (with JetPack Compose roots), kotlinx.coroutines.
- Backend integration through REST APIs for model deployment management.
- Agent layer involves configuration files in TOML/JSON/YAML and LLM proxy routing.
- Packaging includes native installers: MSI (Windows), DEB (Linux), DMG (macOS).
- Nice-to-have tooling includes mitmproxy for HTTP debugging and LiteLLM/OpenRouter-style proxy layers.
Challenges:
- Build a desktop control plane for local AI agents that simplifies running LLMs on heterogeneous hardware.
- Address model lifecycle, proxy routing, agent configuration, and OS-specific quirks while keeping the system extensible.
- Visualize model statistics and system load on a backend that handles deployment.
Team:
- Small, startup-like team with no bureaucracy, direct user contact, and fast iteration.
- Code reviews are part of the process.
- Join a small, startup-like team focused on building a desktop tool for local AI inference.
- Work with Kotlin and Compose Desktop to develop an application that deploys, configures, and manages AI models on local devices.
- Daily tasks include building the UI in Compose Desktop, integrating with backend REST APIs for model deployment, and setting up agent configurations using TOML/JSON/YAML files.
- Involve in LLM proxy routing and creating installers for Windows, macOS, and Linux.
- The team has an internal MVP and is in direct communication with potential users, aiming to make the tool open source.
- Opportunity to shape a developer tool from its early stages.
Project Scope:
- Develop a desktop application for deploying and configuring local inference on devices like NVIDIA Spark/DGX Spark.
- Manage model lifecycle (start/stop) and connect coding agents like Claude Code and Codex to locally hosted models.
- Currently an internal MVP, with plans to open source.
Tech Stack:
- Kotlin, Compose Desktop (with JetPack Compose roots), kotlinx.coroutines.
- Backend integration through REST APIs for model deployment management.
- Agent layer involves configuration files in TOML/JSON/YAML and LLM proxy routing.
- Packaging includes native installers: MSI (Windows), DEB (Linux), DMG (macOS).
- Nice-to-have tooling includes mitmproxy for HTTP debugging and LiteLLM/OpenRouter-style proxy layers.
Challenges:
- Build a desktop control plane for local AI agents that simplifies running LLMs on heterogeneous hardware.
- Address model lifecycle, proxy routing, agent configuration, and OS-specific quirks while keeping the system extensible.
- Visualize model statistics and system load on a backend that handles deployment.
Team:
- Small, startup-like team with no bureaucracy, direct user contact, and fast iteration.
- Code reviews are part of the process.
Compensation & benefits
Salary: PLN 252k – PLN 373k
Building tech community
Flexible hybrid work model
Home office reimbursement
Language lessons
MyBenefit points
Private healthcare
Training Package
In-house training
B2B contract
About TechTree's client
A leading European software consulting and engineering company is home to over 350 EU-based professionals. Our mission is to craft clean code and practical solutions with precision and purpose. We foster a dynamic culture rooted in strong engineering, a sense of ownership, and transparency, empowering our team. As part of an expanding group, we offer a compelling environment for those seeking to make a substantial impact in the software industry within a forward-thinking organization.
Team
- Small, startup-like team on the JetBrains side