Staff Software Engineer, Agentic Platform

Docker has been one of the most loved brands in developer tooling, trusted by more than 20 million monthly users and over 20 billion container image pulls. From solo founders to the world's largest companies, developers rely on Docker to build, share, and run their applications across our suite of products including Docker Desktop, Docker Hub, and Docker Scout. We are a globally distributed, remote-first team building the tools that define how software gets built and delivered. As AI agents redefine software development, Docker is at the center of that shift, providing the sandboxed environments, verified images, and secure infrastructure that make autonomous workflows trustworthy by default. Join Docker's Agentic Platform team to build the foundational infrastructure powering the next generation of AI-driven workflows. Intelligent agents are rapidly becoming the primary interface between developers and complex systems and we're building the platform that makes them reliable, scalable, and observable at production scale. You'll be working on the core agent execution runtime, orchestration primitives, and the cloud infrastructure that keeps the Agentic Platform running 24/7. This is a high-ownership role: you won't just build systems, you'll run them, respond when they fail, and drive continuous improvement across the stack. This is a greenfield opportunity to shape how agents are built and operated at scale. You'll work alongside seasoned engineers, collaborating with partner teams across AI infrastructure, developer experience, and platform reliability. Please note: for this role, we are prioritizing candidates who currently live in the West Coast (Pacific) time zone of the USA. Responsibilities/What you'll work on: Agent Workflow & Orchestration Design and operate the core agent execution runtime responsible for scheduling, state management, and lifecycle management of long-running agentic workflows Build robust multi-agent coordination patterns: task handoff, agent memory (short-term and long-term), tool use, and workflow branching at scale Develop context window management strategies and session persistence layers for stateful agent interactions Build tooling for prompt engineering as a first-class engineering discipline — versioning, testing, and evaluation of prompts at scale Build platform capabilities that support developers working in AI-assisted coding workflows, including IDE integrations, local-first development environments, and fast iteration loops Cloud Infrastructure & Service Ownership Own and operate Agentic Platform services in AWS or OCI infrastructure provisioning, scaling, cost management, and reliability Provision and manage cloud infrastructure using Terraform; manage Kubernetes application packaging and deployment with Helm Participate in the 24/7 on-call rotation This role may require participation in a 24/7 on-call rotation for the Agentic Platform; carry genuine pager responsibility for the services you build and operate Define and uphold SLOs; lead incident response, blameless post-mortems, and drive continuous reliability improvements Instrument systems for observability: distributed tracing, structured logging, metrics dashboards, and alerting Technical Leadership As a Staff Engineer, partner with engineering leadership to set technical direction and serve as a guide and mentor as the team grows Drive architectural decisions that balance velocity with long-term maintainability across a distributed, cloud-native stack Collaborate cross-functionally with product managers, designers, and partner engineering teams to integrate agentic capabilities into the broader developer platform Contribute to a culture of engineering excellence through design reviews, RFC processes, and mentorship Qualifications for this role Required: 8+ years of professional, hands-on, full-time software engineering experience in backend, infrastructure, or platform engineering. Cloud Platform Expertise (AWS/OCI/Azure/GCP): Proven, hands-on experience operating production services in AWS or Oracle Cloud Infrastructure compute, networking, managed services, IAM, and cost management. This is a must-have; the Agentic Platform is a cloud-native service running 24/7. Service Ownership in a Cloud Setting: You have owned production services end-to-end — on-call, incident response, SLO definition, and post-mortems. You don't just build; you run what you build. Distributed Systems Design: Deep understanding of fault tolerance, consistency, observability, and scalability in cloud-native environments Backend Engineering Proficiency: Strong proficiency in at least one backend language used for systems work — Go, Python, Rust, or Java Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience Strongly Preferred: Go: Professional proficiency in Go — Docker's primary language for backend systems Infrastructure as Code: Experience with Terraform for cloud infrastructure provisioning and Helm for Kubernetes application packaging and deployment Data Infrastructure: Experience with PostgreSQL and Redis / Pub-Sub patterns for state management, caching, and event-driven agent workflows MCP & Agent Tooling: Experience with MCP (Model Context Protocol) server design and integration Container & Orchestration: Docker, Kubernetes, or equivalent — especially in the context of agent sandboxing and secure code execution environments AI-assisted development tools: Familiarity with Cursor, Claude Code, Copilot, Windsurf, etc. and the developer personas using them Agent Evaluation: Experience with LLM-as-judge frameworks, behavioral regression testing, and golden dataset management Agent Systems Experience: Hands-on experience building or operating AI agent systems — including multi-agent orchestration, tool use, memory systems, or agent evaluation frameworks Open Source: Contributions or community engagement on relevant open source projects Docker considers visa sponsorship on a case-by-case basis based on business needs. We use Covey as part of our hiring and / or promotional process for jobs in NYC and certain features may qualify it as an AEDT. As part of the evaluation process we provide Covey with job requirements and candidate submitted applications. We began using Covey Scout for Inbound on April 13, 2024. Please see the independent bias audit report covering our use of Covey here . Perks Freedom & flexibility; fit your work around your life Designated quarterly Whaleness Days plus end of year Whaleness break Home office setup; we want you comfortable while you work 16 weeks of paid Parental leave (after 6 months of employment) Technology stipend equivalent to $100 USD net/month PTO plan that encourages you to take time to do the things you enjoy Training stipend for conferences, courses and classes Equity; we are a growing start-up and want all employees to have a share in the success of the company Docker Swag Medical benefits, retirement and holidays vary by country Remote-first culture, with offices in Seattle and Paris Docker embraces diversity and equal opportunity. We are committed to building a team that represents a variety of backgrounds, perspectives, and skills. The more inclusive we are, the better our company will be. #LI-REMOTE