Machine Learning Engineer, Risk AI/ML

Details

At Coinbase, our mission is to increase economic freedom in the world by building the emerging onchain platform and future global financial system. The Risk AI/ML team builds sophisticated models that protect customers and make Coinbase a trusted platform in crypto. This hands-on technical role focuses 100% on modeling: designing, deploying, and iterating ML models that prevent fraud, account takeovers, and scams, and enable products like instant guest checkout and Coinbase Cards. The role leverages a centralized, self-service ML platform and expects in-person participation throughout the year (team and company offsites are held multiple times annually).

Responsibilities

• Own end-to-end development of ML models using a centralized, self-service ML platform, from ideation to production.
• Improve core model performance in high-priority pods (Scam Models, Transfer/Transaction Risk Models, Withdrawal Limit Models, Account Takeover models).
• Rapidly respond to 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.
• Build and deploy production-grade AI/ML models and pipelines enabling reliable, real-time predictions using automated CI/CD pipelines and a centralized feature store.
• Apply advanced ML methodologies (deep learning, NLP, Graph Neural Networks, sequence modeling, LLMs for NLP and conversational agents) to solve crypto-native challenges while focusing on modeling rather than infrastructure plumbing.
• Build context-aware risk systems that decide which friction (quiz, LLM agent, human review) to apply to which user to balance security and user experience.
• Collaborate with Risk Operations, Platform Engineering, and Product Management to close the feedback loop and turn new threats into automated defenses.

Requirements

• 4+ years of professional experience in software engineering and/or AI/ML, with experience deploying AI/ML systems into production.
• Passion for Coinbase's mission and a commitment to protecting users from fraud and scams; alignment with core cultural values (add positive energy, communicate clearly, be curious, be a builder).
• Familiarity with applied AI/ML techniques (Risk ML, deep learning, NLP, recommender systems, anomaly detection).
• Proficient coding skills (e.g., Python) and experience with AI/ML frameworks such as TensorFlow and PyTorch.
• Experience building backend systems with a focus on data processing or analytics is a plus.
• Strong collaboration and communication skills, able to convey technical concepts to technical and non-technical audiences.

Nice to Haves

• Bachelor's degree in Computer Science, AI/ML, Data Science, or a related field.
• Familiarity with modern data and AI/ML infrastructure: Feature Stores (e.g., Tecton), Model Serving (e.g., RayServe), Apache Airflow, Spark, Kafka.
• Experience with Graph Neural Networks (GNNs), Sequential Models (LSTMs), LLMs (NLP, fine-tuning, agentic systems), or Reinforcement Learning.
• Understanding of MLOps best practices, including monitoring and improving production models.
• Experience with data analysis and visualization tools.

Compensation & Benefits

• Pay Range: $152,405—$179,300 USD (target annual salary depending on work location).
• Full-time offers include bonus eligibility, equity eligibility, and benefits (medical, dental, vision, 401(k)).
• Additional benefits: Health Savings Account contributions, disability and life insurance, wellness stipend, mobile/internet reimbursement, connections stipend, volunteer time off, fertility counseling and benefits, generous time off/leave policy, option to get paid in digital currency.

Additional Notes

• Job ID: GPML04US.
• Coinbase is remote-first but not remote-only; in-person participation and attendance at offsites are expected and supported.
• Coinbase is an Equal Opportunity Employer and provides reasonable accommodations for applicants with disabilities. US-specific applicant resources and notices are provided in the posting.
• The role may participate in pilots for AI-powered interview tools; human recruiters will review responses. Contact accommodations[at]coinbase.com for disability-related accommodations.