Skip to content

Senior Software Engineer - Bits AI SRE

Builds reliable AI-powered systems for Bits AI SRE at Datadog, focusing on chat, remediations, and codefixes to resolve production issues. Requires 5+ years backend experience in Go, LLM prompt engineering, and productionizing AI workflows.

187k – 240kNew York, NYDevOps / SREHybrid5+ YOE

About the role

What You'll Do

  • Work closely with product managers, designers, and engineers to build and iterate on AI-powered product experiences in Bits AI SRE.
  • Develop customer-facing systems across chat, remediations, and codefixes that help users resolve production issues more quickly.
  • Work on prompts, evaluation loops, and backend systems to make applied AI workflows reliable, useful, and production-ready.
  • Prototype quickly, test what works in the real world, and iterate rapidly to ship new product capabilities.
  • Build the infrastructure and product logic needed to connect AI outputs to meaningful actions, including operational remediations and generated code changes.
  • Collaborate with partner teams across Datadog to expand remediation capabilities and integrate with systems that support investigation, automation, and code generation.
  • Follow the latest developments in LLM prompting, agent design, and applied AI product development, and bring strong judgment about what is practical to use in production.

Who You Are

  • Engineer with at least 5 years of professional experience, strong backend engineering skills and product mindset.
  • Experience building production systems in Go (or similar) and worked with LLM-based systems.
  • Experience with prompt engineering, evaluation, and iteration for LLM-powered systems.
  • Strong engineering fundamentals to productionize AI features.
  • Comfortable in fast-moving environment with high ambiguity.
  • Bonus: Experience with Kubernetes or production remediation/operational automation systems.
  • Requirement: Demonstrated ability to use AI coding tools and refine AI-generated output.

Benefits and Growth

  • Build tools for software engineers and use them to accelerate development.
  • Influence on product direction and business impact.
  • Work with skilled teammates.
  • Competitive global benefits and continuous professional development.

Salary: $187,000—$240,000 USD

Skills

GoLLMsPrompt EngineeringKubernetesBackend EngineeringAi SystemsObservabilityRemediationAutomationEvaluation Loops

Similar roles

DevOps / SRE jobs

Senior Software Engineer - Linux Kernel/eBPF

Build and maintain eBPF-based network monitoring in the Datadog Agent, working at the intersection of the Linux kernel and network infrastructure. Requires deep Linux kernel experience and 5+ years building high-throughput, low-latency systems.

187k – 240kNew York, NYDevOps / SREHybrid5+ YOECTcp

Senior Systems Engineer

Senior Systems Engineer owns end-to-end feature domains across vehicle, autonomy, and operations for mobility-as-a-service. Leads cross-functional teams through full product lifecycle, creates requirements and MBSE models, requiring 8+ years experience and bachelor's in engineering/CS/physics.

187k – 225kFoster City, CADevOps / SREOn-site8+ YOEMbseJama

Senior Software Engineer, Infrastructure

Senior engineer building and standardizing AWS/GCP cloud infrastructure, networking, and self-service tooling for Coinbase's multi-cloud platform.

186k – 219kUnited StatesDevOps / SRERemote5+ YOEGoAWS

Senior Software Engineer, Infra - Compute Platform

Senior engineer owning Kubernetes-based compute orchestration platform. Builds tooling, automation, and AI-driven workflows to improve reliability and developer experience across Coinbase services.

186k – 219kUnited StatesDevOps / SRERemote5+ YOEAWSGCP

Senior Site Reliability Engineer, Core AI Infrastructure

Senior SRE owning reliability, monitoring, and automation for Coinbase's AI infrastructure on AWS and Kubernetes. Requires 5+ years cloud automation experience and strong incident response skills.

186k – 219kUnited StatesDevOps / SRERemote5+ YOEGoAWS