Profile cover
H

AI API Usage Anomaly Detection Developer

Uelvex Cloud

Remote · $60k – $80k / year · Full-time · Posted 5 months ago

No longer accepting applications

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

When an API client suddenly sends 10x more requests than usual, is it a successful product launch or a runaway script that's about to blow through their rate limit and crash our infrastructure? When a client's error rate jumps from 2% to 15%, is it their bug or ours? Our usage anomaly detection system answers these questions automatically, alerting both clients and our ops team before problems escalate. You'll build the anomaly detection models that learn normal usage patterns for each API client — request volume curves, error rate baselines, endpoint distribution, and payload size profiles — and flag deviations that warrant attention. The system monitors 890 million requests per month across 200+ clients, so the detectors need to be efficient and the alerts need to be precise. The platform reliability team is four engineers. You'll start with the volume anomaly detector, which is the most straightforward statistically, and progress to more nuanced detectors as you learn the domain. Your senior teammate handles the alerting and escalation logic; you'll provide the anomaly signals.

Fully remote.

Responsibilities

  • Build usage anomaly detection models for API request patterns
  • Learn per-client baselines for volume, error rates, and endpoint distribution
  • Design alerting thresholds that balance sensitivity with false alarm rates
  • Monitor detection quality across 200+ API clients
  • Investigate flagged anomalies to refine detection rules
  • Document anomaly patterns for the reliability team knowledge base

Requirements

  • 1+ year of Python development with data analysis experience
  • Basic understanding of statistical anomaly detection concepts
  • Familiarity with SQL for querying usage data
  • Interest in API infrastructure and reliability engineering
  • Systematic approach to investigating data patterns

Benefits

  • Fully remote with flexible hours
  • Health and dental insurance
  • $1,500 learning stipend
  • Mentorship from senior reliability engineers
  • Work on infrastructure handling 890M monthly requests

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

MLOps & AI Infrastructure Data Science & Analytics

Skills

python sql docker aws pandas

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Site Reliability Engineer - (Canada-Remote)

ClickHouse

Full-time Senior

Senior Site Reliability Engineer - (US-Remote)

ClickHouse

Full-time Senior

Senior Solution Engineer

Snowflake

Full-time Senior

Machine Learning Engineer, Core Experimentation

OpenAI

Full-time

Staff Validation Systems Engineer, AI Validation

Wayve

Full-time Staff

GTM Systems Administrator, EMEA

Harvey

Full-time

Job Type

Full-time

Level

Junior

Language

English

Salary Range

$60k – $80k / year

AI Expertise

MLOps & AI Infrastructure Data Science & Analytics

Skills

python sql docker aws pandas statistics

Ready to apply for this role?

Create a free talent account.

  • Find AI roles in one place
  • Get AI-matched job recommendations
  • Reply to companies that message you
  • Build your public AI talent profile
Create free profile and apply Log in

This role is closed. Create your free profile to apply to similar open roles.

Don't miss the next one: get matched to new roles like this.

Create free profile