Docker seeks to build cutting-edge AI agents and tools that transform how developers write code, debug issues, deploy applications, and respond to incidents, to improve developer productivity and experience
Requirements
- 5+ years building production-grade backend systems or developer-facing tools
- Hands-on experience with AI/ML technologies such as practical production experience with LLM APIs (OpenAI, Anthropic, etc.), prompt engineering, or AI agent development
- Proficiency in Go (preferred), Rust, Java, or Python with strong software engineering fundamentals
- Experience designing and building distributed systems, microservices, or platform infrastructure
- Strong understanding of cloud-native systems (AWS, GCP, or Azure), APIs, and data stores
- Solid grasp of CI/CD, automated testing, code review practices, and modern development workflows
- Product-minded approach to building developer tools with focus on user experience and measurable outcomes
Responsibilities
- Build AI-Powered Developer Tools: Design, implement, and ship production-ready AI agents and tools that accelerate developer productivity such as code review and refactoring assistants, automated test generators, local environment setup tools, deployment pipeline diagnostic agents, and on-call assistance tools
- Implement LLM Integrations: Build robust, production-grade integrations with LLM APIs (OpenAI, Anthropic, etc.) such as prompt engineering, response parsing, error handling, rate limiting, cost management, and performance optimization
- Develop Agent Orchestration Systems: Create agent frameworks and orchestration systems that enable complex multi-step workflows, tool calling, context management, and agent-to-agent communication
- Contribute to Platform Infrastructure: Build self-service platform capabilities that enable teams across Docker to rapidly deploy and operate their own AI developer tools such as deployment pipelines, observability integration, security controls, and operational tooling
- Drive Adoption of AI-Native Development: Build tools and programs that accelerate adoption of AI developer tools such as Claude Code, Cursor, and Warp across Docker's engineering organization
- Ensure Production Quality: Write well-tested code with strong test coverage (unit, integration, end-to-end); establish monitoring, alerting, and operational excellence for AI systems
- Collaborate Cross-Functionally: Partner with Principal Engineer on architecture, work with product and design teams on features and UX, and collaborate with platform teams (Infrastructure, Security, Data) on integrations
Other
- Excellent communication skills in remote, asynchronous environments with ability to document technical decisions clearly
- Ownership mentality with bias for action and iterative delivery
- Comfortable working autonomously across distributed teams and navigating ambiguity
- 16 weeks of paid Parental leave
- Freedom & flexibility; fit your work around your life
- Designated quarterly Whaleness Days plus end of year Whaleness break