AI SLA Breach Prediction Engineer

Quelva Works

Remote · $130k – $160k / 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

We run the AI workflow layer for 300+ operations teams, processing 40M+ tasks per month. SLA adherence is the metric our clients care about most — and right now, they find out about breaches after they happen. By then, it's a customer service problem, not an engineering one. The SLA Breach Prediction Engineer role is about changing that timeline. You'll build models that flag at-risk tasks 30, 60, and 120 minutes before their SLA deadline, giving operations teams time to intervene. This requires real-time feature engineering from Kafka event streams, a prediction API with sub-100ms latency, and tight integration with our alerting infrastructure. You'll work on a team of 5 platform engineers and own prediction from training through production monitoring. The first version ships to 10 design-partner clients — your models will run at scale from day one.

Fully remote.

Responsibilities

Build real-time feature extraction from Kafka task event streams
Develop binary and time-to-breach prediction models for at-risk task identification
Deploy prediction API on FastAPI with sub-100ms p99 latency target
Integrate predictions with the alerting and escalation system
Own model retraining triggers and drift monitoring in production

Requirements

5+ years in applied ML with real-time production systems experience
Strong Python skills and experience with streaming feature pipelines
Familiarity with Kafka or equivalent event streaming systems
Experience designing low-latency inference APIs
Prior work in workflow orchestration, logistics, or operations analytics preferred