ML Engineer – Detection for AI-Driven Threat Defense

Quiet Capital; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Free lunch and dinner in the office

Flexible PTO

Quarterly team offsites

Job summary

Doppel is building AI-native defenses against social engineering threats. We are seeking a machine learning engineer to design, train, and deploy models for both batch and real-time inference, across diverse data sources.

You will work with Detection and Infrastructure teams to scale ML systems as web data grows, tackling NLP, embeddings, similarity search, classification, and anomaly detection. You will partner with customers and internal stakeholders to translate real-world threats into

Qualifications

• Experience designing, training and deploying ML models in production environments.
• Experience with NLP, embeddings, and similarity search.
• Ability to work on problems from NLP to anomaly detection and classification.
• Ability to translate real-world threats into production ML systems.

Responsibilities

• Design, train, and deploy models for batch and real-time inference across diverse data sources.
• Collaborate with Detection and Infrastructure teams to scale ML systems with web data ingestion volume.
• Work on NLP, embeddings, similarity search, classification, and anomaly detection.
• Collaborate with customers and stakeholders to translate real-world threats into production ML systems.

Skills

Machine Learning

NLP

Embeddings

Similarity search

Classification

Anomaly detection

Production ML systems

Distributed processing

Job description

Doppel is building AI-native defenses against social engineering threats. We are seeking a machine learning engineer to design, train, and deploy models for both batch and real-time inference, across diverse data sources.

You will work with Detection and Infrastructure teams to scale ML systems as web data grows, tackling NLP, embeddings, similarity search, classification, and anomaly detection. You will partner with customers and internal stakeholders to translate real-world threats into