AI Root Cause Analysis Automation Engineer

Ulvex Systems

Remote · $160k – $200k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

During a P1 incident, every minute of mean time to resolution costs real money. Our platform monitors 220 enterprise customers' production environments, collecting 800GB of telemetry per day. When something breaks, the on-call engineer opens a dashboard and starts investigating. The problem: they spend 40 minutes reading logs and correlating signals before they understand what happened. We want to cut that to 5 minutes. Root cause analysis automation is genuinely hard. Symptoms appear in one service; the cause is three hops upstream. The causal graph changes with every deployment. Standard approaches — threshold alerts and runbook lookups — miss the non-obvious correlations. We're building a system that uses causal inference, anomaly correlation, and LLM-assisted log analysis to generate a ranked hypothesis list that's right the first time 75% of the time. You'll own this system. You'll design the causal inference framework, build the anomaly correlation engine, integrate the LLM analysis layer, and measure the system against historical incident records where the true root cause is known. This is a staff-level problem requiring both ML depth and production operations judgment.

Fully remote.

Responsibilities

Design a causal inference framework for production incident root cause analysis
Build anomaly correlation engine across distributed telemetry signals
Integrate LLM-assisted log analysis for hypothesis generation and ranking
Evaluate system accuracy against historical incident ground truth records
Optimize inference latency to produce hypotheses within 60 seconds of incident detection
Work with customer SRE teams to validate and refine hypothesis quality

Requirements

7+ years in ML engineering or SRE with production observability experience
Experience with causal inference, time series correlation, or anomaly detection at scale
Strong Python and system design skills
Deep understanding of distributed systems and common failure patterns
Track record reducing MTTR through automated tooling