AI Latency Profiling Automation Developer

Covex Cloud

Remote · $80k – $100k / year · Full-time · Posted 5 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

When a serverless ML function takes 800ms instead of 200ms, is it a cold start? A memory pressure issue? A network round-trip to a bloated dependency layer? Finding the root cause today requires an experienced engineer running manual profiling tools. We automate that diagnosis. Our latency intelligence platform instruments serverless and containerized ML workloads, collects distributed traces, and runs automated root cause analysis to tell on-call engineers exactly where latency is coming from — not just that it is slow, but why, and specifically which code path, dependency, or configuration is the bottleneck. You'll build the root cause classification models: the ML layer that translates raw trace and metric patterns into human-readable diagnosis reports. The classification needs to work across diverse technology stacks — Lambda, Cloud Run, ECS, and custom Kubernetes deployments — so generalization is the core challenge.

Fully remote.

Responsibilities

Build root cause classification models for serverless and container latency anomalies
Design features from distributed trace patterns, timing histograms, and resource metrics
Develop generalization strategies for classification across diverse technology stacks
Create human-readable diagnosis reports from model predictions
Build evaluation benchmarks from labeled incident postmortems
Collaborate with platform engineers on trace collection infrastructure improvements

Requirements

3+ years in platform engineering or ML engineering with observability domain experience
Experience with distributed tracing, profiling tools, or performance debugging
Strong Python skills and statistical reasoning for latency analysis
Familiarity with serverless and container deployment architectures
Ability to translate technical patterns into clear non-technical explanations