Staff Software Engineer, AI Developer Tools

This is a fully remote position, open to applicants in California, +1 more state.

📋 Description

• Define the technical vision and take ownership of the architecture for AI-driven developer tools and the self-service AI developer tools platform.

• Transform vague challenges into specific requirements, plans, and staged decision-making processes.

• Develop and implement patterns and standards for LLM integration, agent development, and production-level AI systems.

• Influence deployment, observability, security, and operational functionalities for AI developer tools.

• Architect dependable, scalable infrastructure for hosting AI agents and developer tools.

• Advise on AI technologies, LLM providers, and strategies for agent orchestration.

• Design, build, and manage production AI agents for tasks such as code reviews, test generation, deployment diagnostics, and incident management.

• Create self-service platform features that expedite the time-to-production for new AI tools.

• Foster the adoption of Claude Code and Codex within Docker engineering.

• Establish standards for reliability, security, performance, monitoring, incident response, service level objectives (SLOs), and cost management.

• Integrate AI developer tools with continuous integration/continuous deployment (CI/CD), observability, and deployment systems.

• Engage in on-call rotations and enhance alerts, runbooks, and tooling.

• Assess emerging AI/LLM technologies, trends in developer tooling, and frameworks for agents.

• Define metrics for assessing AI tool adoption, productivity improvements, and developer satisfaction.

• Lead technical project delivery across teams including Infrastructure, Security, and Data.

• Mentor senior engineers and facilitate design and code reviews.

• Produce reusable patterns, documentation, and architectural decision records.

• Contribute to the establishment of shared AI-assisted engineering workflows and controls.

⛳️ Requirements

• Over 8 years of experience in software engineering.

• Practical experience in building LLM-driven applications, AI agents, or AI-assisted developer tools.

• Strong familiarity with LLM APIs, including those from OpenAI and Anthropic.

• Experience in prompt engineering.

• Knowledge of agent orchestration frameworks.

• Proven experience in designing scalable distributed systems and developer-centric platforms.

• Hands-on experience with Kubernetes, GitOps deployment patterns, observability systems, and CI/CD pipelines.

• Proficient in programming languages such as Go, Rust, Java, or Python, with a preference for Go.

• Background in designing developer tools, platform systems, or internal tools.

• Experience in clarifying requirements and constraints with stakeholders.

• Proven ability to lead cross-team initiatives and influence without direct authority.

• Strong judgment regarding products and platforms.

• Effective written and verbal communication skills suitable for a remote, asynchronous work environment.

• Experience mentoring seasoned engineers.

• Demonstrated ownership mentality and ability to deliver iteratively in uncertain situations.

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

• Preferred experience with MCP or similar AI agent integration standards.

• Desirable background in developer productivity, DevOps, SRE, or platform engineering.

• Contributions to open-source AI tools, developer tooling, or platform engineering projects are advantageous.

• Experience in evolving an internal platform into a widely adopted production-grade service is preferred.

• Knowledge of security, compliance, and operational practices relevant to production AI systems is a plus.

• Familiarity with Terraform, Pulumi, AWS, GCP, or Azure is preferred.

• Must be eligible to work in the United States.

• Participation in an on-call rotation outside of standard business hours may be required.

🏝️ Benefits

• Equity provided for all full-time employees.

• Remote-first work environment, allowing work from home.

• Flexible work scheduling.

• Generous paid time off (PTO).

• Quarterly Whaleness Days.

• End-of-year Whaleness break.

• Support for home office setup.

• Technology stipend of US$100 net per month.

• Annual learning and development stipend for conferences, courses, certifications, and ongoing education.

• 16 weeks of paid parental leave after six months of employment.

• Comprehensive medical benefits.

• Retirement benefits.

• Paid holidays.

• Docker merchandise.