Principal Machine Learning Architect

Summary

Join Sift, a leading AI-powered fraud platform, as a Machine Learning Architect. Lead the design, implementation, and evolution of large-scale ML systems. Collaborate with cross-functional teams to align ML architecture with business goals. Evaluate and incorporate cutting-edge ML technologies. Establish best practices for model performance and quality. Provide technical leadership and mentorship. Develop a deep understanding of business and customer KPIs. Represent Sift's data science and ML innovations in the industry.

Requirements

• Proven experience building large-scale ML systems in production environments
• Familiarity with tools like Flink, Spark, PyTorch, TensorFlow, or similar frameworks
• Proficiency in not only Python, but also Java, C++, or similar languages
• Knowledge of industry best practices for deploying, maintaining, and scaling ML systems in production
• Experience in high-impact areas such as ad-tech, recommendation systems, personalization, search ranking, or gaming
• Strong understanding of modern ML engineering trends and challenges, including but not limited to model monitoring, drift detection, and retraining strategies
• Knowledge of GenAI, including LLMs, as well as the trends and challenges of building GenAI applications
• Ability to align and lead cross-functional teams on large-scale architectural initiatives
• Demonstrated success in working with diverse stakeholders and fostering alignment around technical and business objectives
• Ability to provide guidance or mentor junior engineers
• Strong critical thinking and ability to approach ambiguous problems systematically
• Curiosity and openness to understand the business impact of technical decisions
• Excellent communication and storytelling skills to articulate architectural vision and influence stakeholders at all levels
• Ability to engage in constructive technical discussions and drive consensus
• Ability to evangelize our data and AI externally, such as with customers, partners, and in the industry

Responsibilities

• Design and architect scalable, reliable, and low-latency (150ms) ML systems for both online and offline use cases
• Ensure systems meet strict performance, latency, and reliability requirements
• Evaluate and incorporate cutting-edge ML trends and technologies while aligning them with the company’s current architecture and goals
• Define a roadmap to transition the ML ecosystem to a more advanced, future-proof state
• Work closely with stakeholders across engineering, product, and data science teams to align technical designs with business priorities
• Create interfaces (programmatic and organizational) that enable collaboration and coordination across teams and systems
• Establish and enforce best practices for maintaining consistent ML model performance in production
• Develop monitoring systems, metrics, and processes to ensure model quality and reliability over time
• Lead large-scale initiatives, such as transitioning to next-generation architectures, and ensure alignment across diverse engineering teams
• Provide mentorship and technical guidance to engineers to foster a culture of excellence
• Develop a deep understanding of business and customer KPIs
• Collaborate with customer-facing teams to understand use cases and ensure the ML systems deliver real-world impact
• Represent the innovation of our data science and ML in the industry

Preferred Qualifications

• Experience building systems in fraud, trust and safety domain
• Experience creating programmatic and organizational interfaces between teams to coordinate complex systems
• Desire and ability to build technology and solve problems that provide true customer value
• Track record of speaking and/or publishing papers at AI/ML conferences