• Build AI Developer Tool Features: Implement features for AI-powered developer tools such as code review assistants, test generators, deployment diagnostics, and on-call assistance tools • Implement LLM Integrations: Build integrations with LLM APIs (OpenAI, Anthropic, etc.) such as prompt engineering, response handling, error management, and performance optimization • Contribute to Platform Infrastructure: Help build self-service platform capabilities such as deployment pipelines, observability integration, security controls, and operational tooling that enable teams to rapidly deploy AI developer tools • Support AI-Native Development Adoption: Contribute to tools and programs that help teams adopt AI developer tools such as Claude Code, Cursor, and Warp across Docker's engineering organization • Write Quality Code: Develop well-tested code with unit and integration tests; follow team coding standards and participate actively in code reviews to learn best practices • Maintain Production Systems: Assist with monitoring, alerting, and troubleshooting production AI systems; participate in incident response and learn operational best practices • Collaborate and Learn: Work closely with Senior Engineers and Principal Engineer on technical designs; ask questions, seek feedback, and continuously improve your skills in AI/LLM technologies and platform engineering • Document Your Work: Create clear technical documentation for features you build; contribute to team knowledge base and help future team members understand systems • Participate in Team Activities: Engage in design discussions, sprint planning, retrospectives, and team activities; contribute ideas for improving developer tools and team processes • Grow Your Expertise: Continuously learn about AI/ML technologies, developer tooling best practices, and platform engineering patterns through hands-on work and mentorship from experienced engineers