Incident Engineer

TL;DR

Incident Engineer (AI/SaaS): Own end-to-end incident response across AI and platform stack with an accent on rapid detection, triage, communication, and resolution. Focus on defining SLAs/SLOs, driving root cause analysis, and improving observability tooling.

Location: Remote (Gurugram listed)

Company

Leading agentic AI platform for enterprise customer experience working with global brands like Delta Airlines, MetLife, MGM, and United.

What you will do

• Own incident lifecycle including detection, triage, escalation, resolution, and postmortems
• Lead war rooms and stakeholder updates during major incidents
• Define and enforce SLAs/SLOs, severity frameworks, and runbooks
• Collaborate with Engineering, ML, and Integrations teams for quick resolutions
• Monitor system health across integrations like agent desks, LLMs, and ASR/TTS pipelines
• Drive root cause analysis, preventive actions, and tooling improvements

Requirements

• 3–6 years in Incident Management, SRE, or Production Support roles
• Strong understanding of distributed systems, APIs, and cloud environments (AWS)
• Experience with observability tools (e.g., DataDog)
• Experience with monitoring/tracing tools like Langfuse or similar
• Excellent communication and stakeholder management skills
• Ability to stay calm under pressure and drive structured resolution

Nice to have

• Exposure to OpenAI or similar LLM platforms
• Experience supporting customer-facing SaaS products
• Automation mindset for runbooks, alert tuning, and incident tooling
• Familiarity with AI/ML systems, LLM integrations, and voice stacks (ASR/TTS)

Culture & Benefits

• Equal opportunity employer committed to diversity
• Part of AI revolution transforming global brands
• Backed by WndrCo, Y Combinator, and Index Ventures