Datadog·Developer Tools

1mo ago

Senior AI Engineer - APM Experiences

Datadog is a cloud monitoring and observability platform providing metrics, logs, traces, and security for modern infrastructure.

Lead end-to-end development of LLM and agent-based features for Datadog's APM Experiences team that help customers detect, resolve, and prevent application performance issues through AI-powered diagnostics and recommendations. Own the full product loop from prototyping through production, collaborating with PM and Design to ship cohesive AI experiences that integrate across Datadog's observability platform.

• ·4+ years building backend or real-time ML systems with focus on simplicity and performance
• ·Proven production experience with LLM/agent features including prompting, tooling, evals, safety guardrails
• ·Strong ML fundamentals: task definition, dataset collection, modeling, evaluation, deployment, iteration
• ·Experience with offline/online evals, golden sets, and automatic regressions for AI systems
• ·Proficiency in Go, Java, or Python with strong API/service design and production ops knowledge