Digitalocean

Overview

The Senior Software Engineer II-Agentic AI will join the Feedback Systems team to design and develop high-throughput backend systems that orchestrate complex execution workflows, interface with isolated execution environments, and process evaluation signals for AI agents.

About Digitalocean

DigitalOcean is a cutting-edge technology company that simplifies cloud and AI, enabling builders to spend more time creating software. They provide a powerful inference cloud, Managed Agents, and robust feedback systems to help customers run AI inference at scale.

Requirements & Eligibility

• 5+ years of software engineering experience building highly concurrent, fault-tolerant distributed systems.
• Deep proficiency in Python and Go (or strong experience in C++/Java with a willingness to master Python and Go quickly).
• Hands-on experience with durable workflow orchestration engines for managing distributed state and long-running asynchronous tasks.
• Strong working knowledge of containerization, virtualization, or secure workload isolation technologies (e.g., Docker, Kubernetes, or microVMs).
• Experience building resilient APIs and handling high-throughput event or message data.
• Strong sense of ownership, excellent communication skills, and the ability to work effectively in a globally distributed team.
• Foundational understanding of interacting with LLM APIs, prompt constraints, and the unique architectural challenges of testing non-deterministic systems.

Key Responsibilities

• Designing, building, and maintaining robust backend services and highly concurrent asynchronous workflows, primarily in Python and Go.
• Integrating backend control planes with isolated, secure execution environments to safely run agents and capture execution artifacts.
• Building and operating scalable APIs (gRPC, REST) to serve as the connective tissue across data pipelines, evaluation engines, and internal platforms.
• Collaborating closely with cross-functional teams to ensure infrastructure reliably supports complex evaluation scenarios and outcome metrics.
• Driving engineering best practices, including code reviews, comprehensive testing, and technical design documentation.
• Monitoring system performance, investigating bottlenecks, and ensuring high reliability of orchestration systems.