Senior Software Engineer, AI Developer Tools

About Docker

Docker has been one of the most loved brands in developer tooling, trusted by more than 20 million monthly users and over 20 billion container image pulls. From solo founders to the world's largest companies, developers rely on Docker to build, share, and run their applications across our suite of products including Docker Desktop, Docker Hub, and Docker Scout.

We are a globally distributed, remote-first team building the tools that define how software gets built and delivered. As AI agents redefine software development, Docker is at the center of that shift, providing the sandboxed environments, verified images, and secure infrastructure that make autonomous workflows trustworthy by default.

_______________________________________________________________________

Docker is looking for a Senior Software Engineer to build AI-powered developer tools and the platform behind them on our AI Developer Tools team. You will work at the intersection of AI, developer experience, and platform engineering, building tools that make Docker's engineers more productive and the platform that lets teams across Docker prototype, deploy, and scale their own AI developer tools.

As a Senior Engineer you will design, build, and operate:

AI-Powered Developer Tools. AI agents and tools that accelerate developer productivity, surface observability insights, and automate operational reviews. You will help teams adopt an AI-native way of working and speed up adoption of tools such as Claude Code and Codex. Examples include AI-powered code review and refactoring assistants, automated test generators and local environment setup tools, deployment pipeline diagnostic agents, and agents that simplify on-call work during incidents.

Self-Service AI Developer Tools Platform. Platform infrastructure that lets product and platform teams across Docker unblock themselves by prototyping, building, and deploying their own AI developer tools, using the patterns and standards the team sets.

You will report to the Senior Manager, AI Developer Tools, and work closely with the team's Principal and Staff engineers, product engineering teams, and platform teams across Docker.

What Would Make Someone Successful in This Role

You are a strong, hands-on engineer who enjoys building at the intersection of AI, developer experience, and platform engineering. You have built software on top of LLMs and AI agents and have a good sense of what works in practice. You care about the people using your tools, and you can tell a tool developers love from one they put up with. You take a feature from a vague request to production: you ask the right questions about requirements, design it sensibly, ship it iteratively, and operate it afterward. You are comfortable in a fast-moving AI landscape and balance quality with pragmatism. You make the engineers around you better through thoughtful code review and by sharing what you learn.

Responsibilities

Building and Operating AI Developer Tools

Design, build, and operate production AI agents for developer productivity, including code review assistants, test generators, deployment diagnostics, and incident response automation

Integrate LLM providers, agent orchestration frameworks, and MCP servers into reliable tools, following the team's patterns and standards

Build systems that help Docker's engineers adopt AI-native development tools

Build integrations between AI developer tools and existing developer infrastructure such as CI/CD pipelines, observability platforms, and deployment systems

Instrument your tools so the team can measure adoption, effectiveness, and developer satisfaction

Self-Service Platform

Build and improve platform capabilities, including deployment pipelines (ArgoCD/GitOps), observability integration (Grafana), security controls, and cost management, that help teams ship their own AI tools faster

Help reduce time-to-production for new products from weeks to days

Contribute to reliability, security, and performance standards for AI systems, including SLOs, monitoring, and incident response

Design and Delivery

Take features and services from requirements to production. Ask about scale, users, and constraints before designing, and write down your assumptions

Write clear design documents for the work you own, and participate in design reviews for the team

Review code thoroughly and share what you learn with the rest of the team

Take part in the team's on-call rotation, and help improve alerts, runbooks, and tooling so the next incident is easier

Follow the AI-assisted engineering practices the team sets: use AI tools critically, validate their output, and stay accountable for what you ship

Collaboration and Growth

Work with the Senior Manager and the team's Principal and Staff engineers to understand priorities and shape your work

Partner with Infrastructure, Security, and Data teams on integrations and shared standards

Help newer engineers get up to speed on the team's tools, patterns, and practices

Keep up with emerging AI/LLM technologies and agent frameworks, and bring useful findings back to the team

Qualifications

Required

6+ years of software engineering experience building and operating production systems

Hands-on experience building LLM-powered applications, AI agents, or AI-assisted developer tools

Working knowledge of LLM APIs (OpenAI, Anthropic, and others), prompt engineering, agent orchestration frameworks, and practical uses of AI in software development workflows

Experience building and operating scalable backend services, distributed systems, or developer-facing platforms

Experience with cloud-native infrastructure, including Kubernetes, CI/CD pipelines, and observability systems

Proficiency in Go (preferred), Rust, Java, or Python, with strong software engineering fundamentals

Experience building developer tools, platform systems, or internal tools that other engineers rely on

Good product judgment: you weigh developer experience and technical trade-offs, and you ask clarifying questions before committing to a design

Clear written and spoken communication suited to a remote, async-first company

Ownership mentality with a bias for action and iterative delivery in ambiguous, fast-moving environments

Comfortable working autonomously in a distributed, remote-first team

Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience

Preferred

Experience with MCP (Model Context Protocol) or similar AI agent integration standards

Background in developer productivity, DevOps, SRE, or platform engineering

Contributions to open source AI tools, developer tooling, or platform engineering projects

Experience with GitOps deployment patterns (ArgoCD) or Grafana-based observability

Familiarity with security and operational practices for production AI systems

Experience with infrastructure-as-code (Terraform, Pulumi) and major cloud platforms (AWS, GCP, Azure)

What to Expect

First 30 Days

Learn Docker's current AI and developer tooling landscape, the team's services, and the architecture decisions made so far

Meet your teammates, including the Principal and Staff engineers, the Senior Manager, and key stakeholders in product engineering

Ship a useful production change in your first weeks, using the team's AI-assisted engineering workflow

Review existing AI tool prototypes and internal experiments to learn what is working and what is not

Shadow on-call and learn the operational profile of the team's services

First 90 Days

Own a feature or service from design to production with measurable impact, such as part of an AI code review agent, a deployment diagnostic agent, or an on-call assistant

Write the design document for work you own and take part in team design reviews

Contribute to the self-service platform's deployment pipeline, observability integrat