Tech Stack

Description

As a Machine Learning Engineer on the Attack Detection team, you will design and implement systems that combine rules, models, and feature engineering to detect email attacks with high recall. You'll analyze gaps, recommend improvements, and contribute to production pipelines while working on a team that protects over 25% of the Fortune 500 from sophisticated threats.

Requirements

• 3+ years experience designing, building, deploying ML applications in text understanding, NLP, computer vision, recommendation systems, or search.
• 1+ years writing stable production pipelines for model training and evaluation.
• Experience with data analytics using SQL, pandas, spark for building data/metric pipelines.
• Ability to understand business requirements and design simplest generalizable ML model/system.
• Systematic approach to debugging data/system issues in ML/heuristic models.
• Fluent with Python and ML toolkits like numpy, sklearn, pytorch, tensorflow.
• Effective software engineering skills: structured, readable, well-tested, efficient code.
• BS degree in Computer Science, Applied Sciences, Information Systems, or related field.

Responsibilities

• Design and implement systems that combine rules, models, feature engineering, and business inputs into an email detection product.
• Understand features distinguishing safe emails from attacks and how model stack catches them.
• Identify and recommend new feature groups or ML model approaches to improve detection efficacy.
• Work with infrastructure engineers to productionize signals.
• Write code with testability, readability, edge cases, and errors in mind.
• Train models on defined datasets to improve efficacy on specialized attacks.
• Monitor and improve false negative rates and efficacy rates through feature engineering, rules, and ML modeling.
• Analyze FN/FP datasets to categorize capability gaps and recommend short-term feature/rule improvements.
• Contribute to building and debugging data pipelines or presenting results to customers.