Senior Software Engineer – AI Reliability & Automation

Openkrill; United States; Remote; USD 140,000 - 200,000; Full time

Benefits offered by this job

Competitive compensation

AI native culture

Health & Wellness

Flexible time off

Growth & learning

Remote-first culture

Job summary

Atlan is hiring for its Reliability team to advance autonomous AI operations in production. You will build and validate agent reliability, design gates for safe production use, and expand auto-remediation with scalable, audited playbooks.

The role emphasizes delivering trustworthy, scalable systems that other teams can adopt and rely on. You’ll work in a mature codebase with documented architecture decisions, contributing to wide adoption across the organization and shaping the future of

Qualifications

• You’ve lived operational toil and owned incidents end to end.
• You remove classes, not tasks, by eliminating recurring problems.
• You measure impact with adoption and real denominators, not just claims.
• You’ve rewritten core workflows with AI, making them AI-native.
• You understand failure modes, false-positives, rollback paths and blast radius.
• You’ve built platforms that other teams adopt and trust.
• You can join a high‑rigor codebase and improve it quickly.

Responsibilities

• Make investigation agents accurate and trustworthy, not just fast.
• Grow auto-remediation coverage across more playbooks with safe, staged autonomy.
• Own evals and benchmarks for when an agent is trusted in production.
• Design production gates: fail-closed checks, kill switches, approval flows and blast-radius limits.
• Build new agents that remove toil and make future agents cheaper to ship.
• Develop a platform with clean interfaces and guardrails for cross-team adoption.
• Deliver urgent fixes when something is on fire, then remove the root cause.

Job description

Atlan is hiring for its Reliability team to advance autonomous AI operations in production. You will build and validate agent reliability, design gates for safe production use, and expand auto-remediation with scalable, audited playbooks.

The role emphasizes delivering trustworthy, scalable systems that other teams can adopt and rely on. You’ll work in a mature codebase with documented architecture decisions, contributing to wide adoption across the organization and shaping the future of