Coinbase is seeking to build sophisticated Machine Learning models to protect its customers from fraud, account takeovers, and scams, thereby establishing itself as the most trusted platform in crypto and enabling future products.
Requirements
- 4+ years of professional experience in software engineering and/or AI/ML, with experience deploying AI/ML systems into production.
- Familiarity with applied AI/ML techniques (e.g., Risk ML, deep learning, NLP, recommender systems, anomaly detection).
- Proficient coding skills (e.g., Python) with experience in AI/ML frameworks (TensorFlow, PyTorch).
- Experience in building backend systems with a focus on data processing or analytics is a plus.
- Familiarity with modern data and AI/ML infrastructure (e.g., Feature Stores like Tecton, Model Serving like RayServe, Apache Airflow, Spark, Kafka).
- Experience with Graph Neural Networks (GNNs) or Sequential Models (like LSTMs).
- Experience with LLMs (NLP, fine-tuning, agentic systems) or Reinforcement Learning.
Responsibilities
- Use our centralized, self-service ML platform to own the end-to-end development of ML models, from ideation to production.
- Enhance our core models, including the Scam Models, Transfer/Transaction Risk Models, Withdrawal Limit Models, and Account Takeover models.
- Act on new threat data to build, train, and deploy permanent ML models that replace temporary rules—targeting a deploy-to-production timeline of under one week.
- Develop production-grade AI/ML models and pipelines that enable reliable, real-time predictions, leveraging our platform's automated CI/CD pipelines and centralized feature store.
- Apply modern methodologies (e.g., deep learning, NLP, Graph Neural Networks (GNNs), sequence modeling, and LLMs for NLP and conversational agents) to solve complex, crypto-native challenges—all while focusing 100% on modeling, not infrastructure plumbing.
- Build the adaptive logic that decides which friction (a quiz, an LLM agent, a human review) to apply to which user (e.g., new user, high-value trader), balancing security with user experience.
- Work closely with stakeholders from Risk Operations, Platform Engineering, and Product Management to close the feedback loop, turning new threats into automated defenses.
Other
- A commitment to building an open financial system and a strong desire to protect users from fraud and scams.
- You embody our core cultural values: add positive energy, communicate clearly, be curious, and be a builder.
- Ability to work collaboratively on technical initiatives and contribute to impactful AI/ML solutions.
- Strong communication skills, with the ability to convey technical concepts to both technical and non-technical audiences.
- In-person participation is required throughout the year. Team and company-wide offsites are held multiple times annually to foster collaboration, connection, and alignment. Attendance is expected and fully supported.
