Staff Software Engineer, AI Developer Tools

Docker is hiring a Staff Software Engineer to set technical direction for its AI Developer Tools team. The role focuses on building AI-powered developer tools and a self-service platform that enables Docker teams to prototype, deploy, and scale AI tools.

Responsibilities:

• Set technical direction and own the architecture for AI-powered developer tools and the self-service platform within the team's roadmap
• Turn ambiguous problems into clear requirements, plans, and staged decisions. Ask about scale, users, and constraints before designing, and write down your assumptions
• Establish patterns, standards, and best practices for LLM integration, agent development, and production AI systems that the team and partner teams adopt
• Shape platform capabilities including deployment frameworks (ArgoCD/GitOps), observability integration (Grafana), security controls, and operational tooling for AI developer tools
• Design reliable, scalable infrastructure for hosting AI agents and developer tools
• Recommend AI technology choices, LLM provider strategies, and agent orchestration approaches, and make the trade-offs explicit
• Work with the Senior Manager and the team's Principal engineers to align technical decisions with business goals
• Design, build, and operate production AI agents for developer productivity, including code review assistants, test generators, deployment diagnostics, and incident response automation
• Build self-service platform capabilities that reduce time-to-production for new AI tools from weeks to days
• Build systems that speed up adoption of AI-native development tools (Claude Code, Codex) across Docker's engineering organization
• Set and meet reliability, security, and performance standards for AI systems, including SLOs, monitoring, incident response, and cost management
• Design integrations between AI developer tools and existing developer infrastructure such as CI/CD pipelines, observability platforms, and deployment systems
• Take part in the team's on-call rotation and use what you learn to improve alerts, runbooks, and tooling
• Evaluate emerging AI/LLM technologies, developer tooling trends, and agent frameworks, and recommend what Docker should adopt and what it should not build
• Define how we measure AI tool effectiveness, including adoption, productivity gains, and developer satisfaction
• Improve AI tool performance, cost efficiency, and developer experience through architectural improvements
• Contribute to the technical approach for hardening proven internal tools so other teams across Docker can adopt them
• Lead cross-team technical delivery, surface risks early, and work with Infrastructure, Security, and Data on shared standards
• Mentor senior engineers on AI/LLM integration patterns, agent development, and platform engineering practices
• Lead design reviews and raise the quality of design and code reviews across the team
• Create reusable patterns, documentation, and architectural decision records (ADRs) that other engineers build on
• Help the team turn good individual AI-assisted engineering practice into shared workflows and controls
• This role may require participation in an on-call rotation to provide support outside of standard business hours, including evenings, weekends, and holidays, as needed

Requirements:

• 8+ years of software engineering experience, with demonstrated technical leadership on production systems at scale
• Hands-on production experience building LLM-powered applications, AI agents, or AI-assisted developer tools
• Strong understanding of LLM APIs (OpenAI, Anthropic, and others), prompt engineering, agent orchestration frameworks, and practical uses of AI in software development workflows
• Track record of designing and building scalable distributed systems and developer-facing platforms
• Production experience with cloud-native infrastructure, including Kubernetes, GitOps deployment patterns, observability systems, and CI/CD pipelines
• Proficiency in Go (preferred), Rust, Java, or Python, with strong software engineering fundamentals
• Experience designing developer tools, platform systems, or internal tools that other teams rely on
• Track record of clarifying requirements and constraints with stakeholders before committing to a design
• Track record of leading complex initiatives that crossed team boundaries, and of influencing without direct authority
• Strong product and platform judgment: you weigh business outcomes, developer experience, and technical trade-offs
• Clear written and spoken communication suited to a remote, async-first company
• Track record of mentoring other experienced engineers
• Ownership mentality with a bias for action and iterative delivery in ambiguous, fast-moving environments
• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience
• 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 evolving an internal platform or tool into a widely adopted, production-grade service
• Knowledge of security, compliance, and operational practices for production AI systems
• Experience with infrastructure-as-code (Terraform, Pulumi) and major cloud platforms (AWS, GCP, Azure)