AI Network Intrusion Pattern Analyst

Delven Labs

Remote · $100k – $130k / 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

Network traffic data is a firehose — 4 billion flow records per day across our client deployments. Somewhere in that torrent are the 200 flows that represent an active intrusion: lateral movement, data exfiltration, command-and-control communication. Finding those 200 flows without generating 10,000 false alerts is the problem we solve. The detection models use graph-based features (communication patterns between hosts), temporal features (activity at unusual hours or durations), and content features (protocol anomalies, payload characteristics). You'll improve detection by building better graph representations of network behavior, designing features that capture attacker tradecraft patterns, and reducing the false positive rate that currently drives alert fatigue in our client SOCs. The threat detection team is six engineers. You'll focus on the feature engineering and model development side while others handle data ingestion and alert delivery. Every model change gets tested against a red team dataset — our own security researchers generate realistic attack traffic to benchmark detection accuracy.

Fully remote.

Responsibilities

Build graph-based features capturing network communication patterns
Design temporal and behavioral features for intrusion detection models
Reduce false positive rates while maintaining detection sensitivity
Evaluate models against red team attack simulations
Analyze missed detections to identify feature gaps
Collaborate with threat intelligence analysts on emerging attack patterns

Requirements

3+ years in ML engineering with network security or anomaly detection experience
Experience with graph-based features and network flow data
Strong Python and distributed computing skills for large-scale data
Understanding of network protocols and common attack techniques
Ability to work with security operations teams on detection requirements