Machine Learning Engineer, Detection

Doppel•New York, NY

About The Position

Doppel is built to outsmart one of the great threats AI presents: mass-manufactured social engineering. Countless scams, deepfakes, and other social engineering attacks are surging across every digital channel: websites, social media, ads, encrypted messaging apps, mobile, and more. Our mission is simple but bold: make the internet a safer place by outsmarting the world’s fastest-evolving digital threats. Backed by a16z and Bessemer and trusted by some of the world’s most recognized brands (OpenAI, United Airlines, Coinbase, etc.), Doppel is growing fast. If you’re driven to solve real-world problems with bold technology, we’d love to meet you. What We're Building We're building the AI-native social engineering defense platform. This means we're designing scalable systems that monitor billions of domains, social media accounts, apps, dark web forums, etc., and leverage AI agents to identify and neutralize digital threats. What We're Looking For We’re looking for a machine learning engineer to help build and scale the models and systems that power Doppel’s detection systems. Check out our blog post on how we set up our ML platform. As an MLE at Doppel, you will Design, train, and deploy models for both batch and real-time inference that identify malicious or infringing content across diverse data sources. Partner closely with the Detection and Infrastructure teams to ensure our ML systems scale with the volume of web data we ingest Work on problems that range from NLP and embeddings to similarity search, classification, and anomaly detection Collaborate directly with customers and internal stakeholders to translate real-world threats into production ML systems

Requirements

Have experience building and deploying ML systems in production environments
Are comfortable working with large-scale datasets and distributed data processing frameworks
Understand the trade-offs between research-quality models and production-ready systems
Are excited about solving real-world problems where the adversary is constantly evolving

Responsibilities

Design, train, and deploy models for both batch and real-time inference that identify malicious or infringing content across diverse data sources.
Partner closely with the Detection and Infrastructure teams to ensure our ML systems scale with the volume of web data we ingest
Work on problems that range from NLP and embeddings to similarity search, classification, and anomaly detection
Collaborate directly with customers and internal stakeholders to translate real-world threats into production ML systems