Sr. Machine Learning Engineer

Join DocuSign to advance machine learning capabilities that help detect and prevent abuse and fraud across its products and services. This hybrid role in Seattle partners closely with Trust & Safety, Fraud, Engineering, Product, Security, and Data teams to strengthen detection as abuse patterns evolve.

Compensation: USD 178,900 - 262,825 per year base salary (varies by geographic location and job-related knowledge, skills, and experience).

Responsibilities

• Design, develop, evaluate, and deploy production ML models for fraud, spam, abuse, and other Trust & Safety risks
• Build risk and reputation scoring capabilities using behavioral, account, network, device, content, and other relevant signals
• Translate detection challenges into ML requirements, including labels, features, evaluation methods, and success criteria
• Detect emerging abuse patterns and determine when ML, rules, or combined approaches improve detection
• Create model outputs that support flagging, throttling, verification, review, or blocking workflows
• Assess detection performance, including false-positive and false-negative tradeoffs and downstream risk impact
• Establish model monitoring, retraining, and degradation detection practices
• Collaborate with Trust & Safety and Fraud experts on adversary behavior and enforcement impact, and with Engineering, Data, Product, and Security on data and production integration
• Set technical direction and define foundational ML practices for Trust & Safety and Fraud

Requirements

• Bachelor’s degree (or equivalent experience) and 8+ years of related industry experience
• Experience developing, deploying, operating, and measuring production machine learning models, including supervised and unsupervised learning, classification, risk prediction, anomaly or behavioral detection, and model evaluation
• Experience applying ML to fraud detection, spam or abuse detection, cybersecurity, Trust & Safety, anti-abuse, risk, or another adversarial domain
• Experience addressing detection problems with incomplete or evolving signals, labels, requirements, or abuse patterns, including changing attacker behavior, class imbalance, noisy labels, model degradation, and false-positive and false-negative tradeoffs
• Experience with C#, Java, or Go, plus ML frameworks, data processing, feature engineering, automation, and reproducible experimentation, training, and validation
• Experience building data and feature pipelines using large-scale behavioral, event, or transactional datasets, including streaming or high-volume event processing
• Experience deploying and serving ML models in distributed systems, integrating outputs into production applications or decisioning systems, and balancing system design, scalability, reliability, latency, throughput, and model performance
• Experience with MLOps across the model lifecycle, including deployment, monitoring, retraining, versioning, degradation detection, and model health, and deploying ML workloads using Docker and Kubernetes
• Experience with observability tools such as Prometheus, Grafana, OpenTelemetry, or Jaeger, and Azure and Azure DevOps (or equivalents)
• Experience defining model success criteria, measuring detection or risk improvements, communicating ML tradeoffs, and collaborating with Product, Engineering, Data, Operations, and domain experts
• Experience building ML systems for spam detection, messaging abuse, account abuse, payment fraud, account takeover, identity risk, reputation scoring, or platform integrity
• Experience building account, entity, or behavioral risk-scoring models that combine multiple signals
• Experience detecting attackers who adapt to controls and integrating ML outputs into automated prevention, enforcement, or risk-based decisioning workflows
• Experience incorporating analyst decisions, investigations, or enforcement outcomes into model development
• Experience improving heuristic detection systems through ML or hybrid rules-and-ML approaches
• Experience establishing or scaling ML capabilities within a fraud, security, or Trust & Safety organization

Technologies

C#, Java, Go, Docker, Kubernetes, Prometheus, Grafana, OpenTelemetry, Jaeger, Azure, Azure DevOps

Benefits

• Bonus: Sales personnel may be eligible for variable incentive pay based on pre-established sales goals. Non-Sales roles are eligible for a company bonus plan calculated as a percentage of eligible wages and dependent on company performance.
• Stock: Eligible for Restricted Stock Units (RSUs).
• Paid Time Off: Earned time off plus paid company holidays based on region.
• Paid Parental Leave: Up to six months off with your child after birth, adoption, or foster care placement.
• Full Health Benefits Plans: Options for 100% employer paid and minimum employee contribution health plans from day one of employment.
• Retirement Plans: Select retirement and pension programs with potential for employer contributions.
• Learning and Development: Coaching, online courses, and education reimbursements.
• Compassionate Care Leave: Paid time off following the loss of a loved one and other life-changing events.

Work Authorization

DocuSign does not provide visa sponsorship or immigration support for this position. Applicants must already be authorized to work in the United States on a full-time, permanent basis without the need for current or future sponsorship.

Location & Work Designation

Seattle, WA (hybrid). Employees divide time between in-office and remote work with access to an office location required. Frequency: minimum 2 days per week, with a weekly in-office expectation that may vary by team.

Job designations at DocuSign are assigned as In Office, Hybrid, or Remote based on the role, and preferred designations are not guaranteed when changing positions. DocuSign may change a position’s job designation depending on business needs and as permitted by local law.