What You'll Do
Lead the technical direction for Docker’s containerized AI agent platform, defining core architecture, APIs, and extensibility models that empower developers to deploy intelligent agents at scale. Design and implement systems that use Docker containers as secure, portable runtimes for AI agents, ensuring performance, isolation, and seamless orchestration.
Advance the open-source cagent project by introducing new features for agent lifecycle management, deployment automation, and cross-environment compatibility. Develop infrastructure that simplifies packaging and running agents locally and in the cloud. Create evaluation frameworks to assess agent behavior, reliability, and readiness for production use.
Set benchmarks for observability, system performance, and operational rigor. Guide incident response and post-mortem analysis to strengthen system resilience. Rapidly prototype and deploy new agent capabilities, moving from concept to production with precision. Collaborate with the Docker Agent community to review contributions and expand ecosystem tooling.
Influence architectural decisions across Docker’s AI initiatives through technical leadership and cross-team collaboration. Mentor senior engineers, elevate code quality through design reviews, and provide clear technical guidance. Participate in on-call rotations to troubleshoot live issues and improve long-term reliability.
Requirements
- 10+ years of software engineering experience, including 3+ years in Staff or Principal-level technical leadership roles
- Strong command of Go; candidates not currently proficient must demonstrate ability and willingness to transition into Go, Docker’s primary backend language
- Hands-on experience with large language models and agent-based development in software workflows
- Proven track record designing and operating scalable, distributed systems in production
- Deep knowledge of Docker, containerization principles, and orchestration patterns
- Experience building platform-level services with robust CI/CD, observability, and security practices
- History of maintaining high-availability systems with a focus on performance and reliability
- Excellent communication skills and ability to lead technical discussions across domains
- Bachelor’s degree in Computer Science, Engineering, or related field, or equivalent real-world experience
Preferred Qualifications
- Experience with AI orchestration frameworks such as CrewAI, AGNO, ADK, LangChain, or LangGraph
- Proficiency in Python for AI prototyping and tool development
- Familiarity with Kubernetes or other container orchestration platforms
- Contributions to open-source projects and community engagement
- Background in agent evaluation, reliability testing, or observability tooling
Benefits
- Flexible work model with remote-first culture and hybrid options
- Quarterly Whaleness Days and an annual end-of-year break
- Home office setup support
- 16 weeks of paid parental leave
- Monthly technology stipend ($100 net)
- Generous PTO policy encouraging personal time off
- Training budget for courses, conferences, and professional development
- Equity participation in a growing startup
- Company swag and remote-friendly culture
- Medical, retirement, and holiday benefits tailored to local regulations
