O

Ollama

Local deployment of LLMs with GPU

Software Engineer - Apps & Agents

AI Application EngineeringConfirmed live in the last 24 hours
Full-timePalo Alto, CA, USANo salary listedIn-person

About the Job

Requirements

  • Experience building a thoughtful developer product used by real people.
  • Strong engineering fundamentals combined with product judgment and visual attention.
  • Ability to own ambiguous work from exploration through implementation and polish.
  • Ability to debug behavior across processes, configuration files, application programming interfaces, native applications, and third-party tools.
  • Ability to simplify complex systems without hiding important behavior from users.
  • Attention to state preservation, recovery, compatibility, and the details that make integrations trustworthy.
  • Comfort working across several parts of the technology stack.
  • Hands-on testing ability and judgment to recognize when technically correct behavior produces a poor user experience.
  • Ability to make decisions in gray areas by weighing user needs, technical constraints, data, and product taste.
  • Ability to use agents to prototype, iterate, and ship to production quickly.

Responsibilities

  • Build and refine Ollama's desktop application, command-line interface, onboarding, and related product surfaces.
  • Make agents and developer tools easy to connect to Ollama.
  • Build first-class integrations and reusable systems that allow others to create and maintain their own integrations.
  • Ensure local and cloud models work reliably across different tools and agent harnesses.
  • Test integrations through real workflows and turn recurring failures into durable compatibility improvements.
  • Work across native applications, Go services and application programming interfaces, and web product surfaces.
  • Partner with model and inference engineers to ship new models with appropriate capabilities, defaults, and integration support.

Desired Qualifications

  • Experience with Go, TypeScript, React, or similar technologies.
  • Experience building an agent, contributing to an agent harness, or modifying one enough to understand how models, tools, context, permissions, and configuration interact.
  • Experience building developer tools, native desktop applications, integrated development environment extensions, or integrations with third-party software.
  • Experience with local inference, hosted models, or products that behave consistently across both.
  • Experience building something with Ollama.

About the Company

Ollama

Local deployment of LLMs with GPU

Ollama provides software to run large language models locally on Windows and other platforms. It enables users to deploy, manage, and accelerate models like Llama 2 and Code Llama, with GPU support and compatibility with the OpenAI Chat Completions API to connect local models with familiar OpenAI tools. The product is licensed software with access to a model library and API services, focusing on local or private deployment rather than cloud usage. Its goal is to let users run AI models on their own hardware with clear licensing and updates, reducing dependence on cloud services.

Company size
51-200
Company stage
Series B
Total funding
$65.1M
Headquarters
Palo Alto, CA
Founded
2021

Recently Posted Jobs

Explore more opportunities at Ollama

See more jobs