Senior Software Engineer II-Agentic AI

About this job

DigitalOcean provides a simple and scalable cloud platform, empowering a community of builders and dreamers around the world. The company's Agentic AI organisation focuses on delivering a powerful inference cloud, Managed Agents, and robust Feedback systems that allow customers to run AI inference safely and securely at scale. As part of the Feedback Systems team, this role involves building the scalable backend infrastructure needed to test and evaluate AI agents reliably. On a normal day, you will design and develop high-throughput backend systems that orchestrate complex execution workflows, interface with isolated execution environments, and handle evaluation signals. You will tackle distributed systems challenges at the intersection of infrastructure orchestration and asynchronous data flows, ensuring that the platforms remain robust, highly available, and scalable to support demanding evaluation scenarios.

Responsibilities

• Design, build, and maintain robust backend services and highly concurrent asynchronous workflows using Python and Go.
• Integrate backend control planes with isolated, secure execution environments to run agents safely and capture execution artifacts.
• Build and operate scalable APIs such as gRPC and REST for data pipelines, evaluation engines, and internal platforms.
• Collaborate with cross-functional teams to ensure infrastructure supports complex evaluation scenarios and outcome metrics.
• Drive engineering best practices including code reviews, comprehensive testing, and technical design documentation.
• Monitor system performance, investigate bottlenecks, and maintain high reliability of orchestration systems.

Requirements

• Have 5+ years of software engineering experience building highly concurrent, fault-tolerant distributed systems.
• Demonstrate deep proficiency in Python and Go, or strong experience in C++ or Java with a willingness to master Python and Go quickly.
• Possess hands-on experience with durable workflow orchestration engines for managing distributed state and long-running asynchronous tasks.
• Have working knowledge of containerization, virtualization, or secure workload isolation technologies like Docker, Kubernetes, or microVMs.
• Show experience building resilient APIs and handling high-throughput event or message data.
• Exhibit a strong sense of ownership, excellent communication skills, and the ability to work in a globally distributed team.
• Possess a foundational understanding of interacting with LLM APIs, prompt constraints, and testing non-deterministic systems.

Who should apply

This role is ideal for experienced software engineers with a background in distributed systems, backend development, and AI infrastructure orchestration. Candidates should have at least five years of engineering experience and strong proficiency in Python and Go. Given the focus on testing non-deterministic systems and interacting with LLM APIs, familiarity with the AI/ML ecosystem is essential. This position is not suited for freshers as it explicitly requires substantial professional experience in building fault-tolerant backend services.

Frequently asked questions