SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Abnormal AI is seeking a Machine Learning Engineer I to join the Misdirected Email Detection (MED) team. This is a highly applied role focused on building, iterating, and experimenting with end-to-end ML solutions for email security. You will own the full ML lifecycle including data wrangling, feature engineering, model training and evaluation, deployment, and monitoring.
Key responsibilities include partnering with Product Managers and Tech Leads to align technical deliverables with roadmap milestones; owning the complete ML pipeline for misdirected email detection with measurable reliability and customer impact; running rigorous experiments and evaluations including offline metrics, online A/B testing, and post-launch monitoring; communicating effectively across distributed teams and maintaining high-quality technical documentation; and participating in shared on-call rotation for owned components, focusing on detection efficacy and real-time scoring systems.
You will be responsible for resolving efficacy-related alerts, investigating high-visibility false positives, and addressing reported false positives/false negatives from customers or internal teams. The role emphasizes a tinkerer's mindset combined with technical rigor, balancing innovation with production excellence to drive experimentation, scale solutions, and deliver reliable detection capabilities that create meaningful customer impact in real-world environments.
Required qualifications include a BS degree in Computer Science, Machine Learning, Artificial Intelligence, Information Systems, or related quantitative field; 1+ years building and operating applied ML features in production systems; proven experience with end-to-end ML systems including data wrangling, feature engineering, model selection, training, evaluation, and production deployment; ability to implement and reason about algorithms and apply numerical computing effectively; demonstrated ability to interrogate production data and launch targeted experiments; understanding of online vs offline pipelines and data labeling workflows; experience running offline metrics, online A/B tests, setting thresholds, and monitoring drift; and strong written and asynchronous communication skills.
Nice-to-have qualifications include experience with Python, Go, AWS, Spark, and Databricks; experience in email security/DLP or misdirected email prevention domains; experience writing detectors/rules to complement ML models; experience operationalizing research into reliable, customer-facing systems; and prior experience contributing to small teams delivering features from scratch.
