Senior Software Engineer II, Agentic AI at DigitalOcean in Seattle, WA

Job description

Dive in and do the best work of your career at DigitalOcean. Journey alongside a strong community of top talent who are relentless in their drive to build the simplest scalable cloud. If you have a growth mindset, naturally like to think big and bold, and are energized by the fast-paced environment of a true industry disruptor, you’ll find your place here. We value winning together—while learning, having fun, and making a profound difference for the dreamers and builders in the world. DigitalOcean is building the infrastructure that enables developers to build, run, and scale AI-powered applications and autonomous coding agents. As a Senior Software Engineer on the MARS (Managed Agent Runtime Services) team, you will help build a production-grade platform for running coding agents and agentic workflows securely, reliably, and at scale. You will design and implement core components of our managed agent runtime, including agent framework integrations, execution environments, control-plane APIs, event-driven infrastructure, and developer-facing APIs and tools. You will work across distributed systems, cloud infrastructure, and emerging agentic AI technologies to make it easy for developers to build sophisticated agents without having to manage the underlying infrastructure. We are looking for a strong engineer who combines deep software engineering fundamentals with pragmatic architectural judgment, end-to-end ownership, and a passion for simplifying complex technology for developers. What You’ll Do Build the managed agent platform: Design, implement, and operate core services for provisioning, executing, managing, and monitoring AI coding agents and agentic workloads. Develop agent framework integrations: Build and maintain integrations with frameworks and runtimes such as OpenAI Codex, Claude Code, CrewAI, and LangGraph, as appropriate to the product roadmap. Design distributed systems: Develop scalable, fault-tolerant services and APIs for agent sessions, lifecycle management, execution orchestration, and asynchronous event processing. Build secure execution environments: Collaborate on sandbox and microVM-based execution, isolation, resource limits, secrets management, network controls, and secure interactions between agents and external services. Enable developer workflows: Build APIs, CLI integrations, SDK-compatible interfaces, and reusable examples that help developers integrate agents, tools, triggers, and external systems into their applications. Improve observability and reliability: Instrument services and agent executions with logs, metrics, traces, and actionable events. Drive improvements in debugging, incident response, performance, and service-level objectives. Own features end to end: Translate product requirements into technical designs, implementation plans, tests, production rollouts, and operational support. Drive technical excellence: Lead design discussions, conduct thoughtful code reviews, improve engineering practices, and proactively address technical debt and operational risks. Collaborate across teams: Partner with product management, infrastructure, security, inference, and developer experience teams to deliver cohesive customer experiences. Explore emerging agent capabilities: Evaluate and prototype agent orchestration, multi-agent workflows, tool execution, human-in-the-loop controls, and usage policies, turning promising ideas into production-ready capabilities. What You’ll Bring to DigitalOcean Distributed Systems Mastery: 8+ years of professional software engineering experience working on microservices, messaging systems, databases, and infrastructure as code, with a heavy emphasis on building large-scale SaaS or PaaS products using Go or similar backend languages. AI/ML Domain Knowledge: Hands-on experience integrating with LLMs or multimodal models, creating, managing & operating Agentic workloads for high scale customers - managing complex multi-day agent session lifecycles, pause/resume tran