Staff Machine Learning Engineer (Platform - Identity)

About the role

This role involves taking ownership of the entire machine learning stack for identity verification at Coinbase. This includes developing and maintaining models for document authenticity, facial recognition, liveness detection, and protection against presentation attacks and deepfakes. The work also extends to building identity-graph systems using Graph Neural Networks to detect coordinated fraud by clustering accounts based on biometric and device signals.

A key part of this position is developing behavioral and device intelligence models. These models will focus on detecting anomalies during capture sessions, distinguishing between human and bot activity, and scoring risk based on device fingerprints, all with real-time performance. The engineer will also be responsible for guiding the company's vendor ML strategy, which includes benchmarking external models, designing dynamic routing logic across different providers, and building internal evaluation systems to prevent regressions.

Success in this role means ensuring the security and integrity of millions of user accounts through advanced machine learning solutions. This involves leading and mentoring other engineers within the team, as well as collaborating with ML Platform and Risk ML teams to ensure consistent ML system design across the company. The ideal candidate will translate compliance requirements and fraud trends into actionable ML roadmaps and effectively communicate technical trade-offs to various stakeholders.

The annual base salary for this role ranges from $218,025 to $256,500 USD, with total compensation potentially including equity and bonus eligibility.

Skills that matter here

• Python: Expert-level proficiency in Python is required for developing and deploying production ML systems.
• TensorFlow: Experience with TensorFlow is necessary for model training, evaluation, and serving infrastructure.
• PyTorch: Experience with PyTorch is necessary for model training, evaluation, and serving infrastructure.
• ML systems: The role requires extensive experience in deploying and leading the architecture of production machine learning systems at scale.
• biometrics: Domain experience in biometrics is essential for developing facial recognition and liveness detection models.
• GNNs: Knowledge of Graph Neural Networks is needed for building identity-graph systems to detect synthetic-identity fraud.

Who this role suits

• You have a strong background in identity verification, biometrics, or account integrity.
• You possess over eight years of experience deploying production ML systems and have led cross-team ML architecture.
• You are adept at translating regulatory requirements and fraud trends into technical ML roadmaps.
• You thrive in an intense, high-bar environment and are comfortable being pushed beyond perceived limits.

From the employer

• Own the full IDV ML stack, including document authenticity models, 1:1 and 1:N face-match, liveness detection, presentation-attack detection, and deepfake/injection detection from feature pipeline through threshold tuning and production enforcement.
• Build identity-graph systems using GNNs that cluster accounts sharing biometric, device, and document signals to detect synthetic-identity rings and coordinated fraud at onboarding.
• Develop behavioral and device-intelligence models for capture-session anomaly detection, bot-vs-human classification, and device-fingerprint-based risk scoring at real-time latency.
• Drive vendor ML strategy by benchmarking external models against a Coinbase-owned evaluation set, designing dynamic routing logic across providers and geographies, and building the in-house evaluation layer that catches regressions before they reach users.
• Lead and mentor senior and mid-level engineers in the pod while partnering with ML Platform and Risk ML teams to align cross-company ML system design.

• 8+ years deploying production ML systems at scale, with proven technical leadership owning cross-team ML architecture from design through production.
• Domain experience in identity verification, biometrics, or account integrity with deep applied ML in at least two of: computer vision/biometrics, GNNs, sequence models, or NLP/LLMs.
• Expert-level Python with production experience in TensorFlow or PyTorch, including model training, evaluation, and serving infrastructure.
• Track record translating KYC/AML requirements and fraud trends into ML roadmaps and communicating trade-offs to Product, Compliance, Risk, and Security stakeholders.
• Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.

• Base salary varies by location (see range below). Total compensation may also include equity and bonus eligibility, and benefits (medical, dental, vision, 401(k)). Annual base salary range (excluding equity and bonus): $218,025—$256,500 USD.
• Coinbase is proud to be an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, creed, gender, national origin, age, disability, veteran status, sex, gender expression or identity, sexual orientation or any other basis protected by applicable law.