Software Engineer II - Risk Engineering

Datadog is hiring a Software Engineer II to strengthen our Risk Engineering program. In this role, you will help design and build AI-powered systems that transform how we manage risk at scale, delivering practical solutions that thoughtfully balance compliance, security, and business objectives. Reporting to the Engineering Manager, you will play a key role in scaling Datadog’s risk management capabilities, driving high-impact engineering outcomes, and evolving our approach to meet emerging technologies and AI-driven workflows. 

This role sits at the intersection of software engineering, LLM systems, and risk automation. You’ll work primarily in Go while building and operationalizing AI-driven tooling centered around large language models (LLMs), prompt engineering, evaluation frameworks, structured data pipelines, and intelligent risk workflows. This is not a traditional backend role, we’re looking for an engineer excited about rapid prototyping, experimenting with LLM capabilities, and turning those experiments into production-grade systems that improve risk visibility and decision-making.

What You’ll Do:

• Develop Go-based services that integrate with LLMs to automate and augment risk workflows.
• Use AI-assisted development tools to accelerate prototyping, iteration, and implementation.
• Design and implement prompt architectures for risk classification, control mapping, exception analysis, and policy interpretation.
• Build structured evaluation frameworks to measure LLM quality, hallucination rates, determinism, and decision accuracy.
• Implement automation for risk management workflows, including triage, remediation tracking, exception handling, and integrations with internal systems, to improve scalability of the program.
• Build evaluation loops to continuously improve prompt performance and model outputs.
• Design schemas and structured data models for risk registers, control libraries, policy exceptions, and evidence artifacts.
• Improve traceability between risks, controls, policies, and exceptions using intelligent automation.

Who You Are:

• You have 2+ years of experience in software engineering, building and operating production systems at scale, including deploying, managing, and troubleshooting services in Kubernetes environments.
• You have hands-on experience with a modern programming language (ideally Go and Python).
• You actively use AI-assisted coding tools (e.g., Cursor, Claude Code, Copilot) and are comfortable building systems.
• Comfort experimenting with LLM APIs (OpenAI, Anthropic, etc.) and building AI-powered tools.
• Experience working with APIs and distributed systems.
• Demonstrated ability to independently break down complex problems, drive solutions, and execute with minimal supervision.
• Strong written and verbal communication skills, with the ability to clearly articulate technical concepts through RFCs, design documents, and architectural diagrams.
• Curiosity about AI systems and their limitations, including an understanding of failure modes such as hallucination, non-determinism, and prompt brittleness.
• Solid foundation in software development best practices, including code quality, testing methodologies, and maintainable, scalable system design.
• Self-motivated and able to take initiative in building programs that scale impact across the organization.