Senior Staff Machine Learning Engineer, Ranking - Revenue

Sequen AI is a leading company in building frontier ranking models for search and recommendations. They are seeking a Senior Staff Machine Learning Engineer to design, develop, and scale innovative ranking and embedding models that power their personalized discovery platform, while embedding within customer systems to ensure effective implementation.

Responsibilities:

• Develop & Optimize Frontier Ranking Models: Build, train, tune, and deploy advanced search and recommendation frameworks using Deep Learning techniques and Learning-to-Rank (LTR) architectures
• Embed and Deliver within Customer Systems: Provide white-glove technical execution inside large consumer enterprise environments, seamlessly integrating Sequen’s ranking platform with existing customer business logic and multi-tenant data ecosystems
• Own ML Production End-to-End: Architect and manage robust model monitoring frameworks, live A/B testing platforms, performance regression detection systems, and automated continuous retraining strategies to ensure sustained revenue impact
• Design Scalable Data Pipelines: Engineer and maintain high-quality production data pipelines using Spark, Airflow, and dbt across AWS and GCP to power both offline model training and real-time online feature scoring
• Codify Repeatable Patterns: Turn bespoke customer implementations into repeatable deployment blueprints, contributing software abstractions and tooling innovations back to Sequen’s core Product and Engineering teams to accelerate future customer velocity
• Maintain Research Dominance: Keep Sequen at the absolute cutting edge by continuously evaluating and incorporating the latest academic and industry breakthroughs in multi-stage retrieval, vector embedding spaces, and large-scale personalization techniques

Requirements:

• 7+ years of professional experience as a Machine Learning Engineer, Applied Scientist, or a highly similar technical role with a strict, demonstrable focus on deep learning for search, recommendations, or web-scale discovery
• Deep mastery of PyTorch, Deep Learning theory, and machine learning algorithms. Proven background designing multi-stage retrieval paths, two-tower embedding architectures, or complex ranking scoring loops
• Hands-on experience manipulating and processing massive, petabyte-scale datasets. Proficient in designing and optimizing pipelines utilizing Spark, Airflow, and dbt across GCP and AWS environments
• Solid working knowledge of cloud-native deployment patterns and infrastructure tooling, including Kubernetes, Docker, Terraform, and AWS to handle model serving scalability and distributed experimentation
• Exceptional critical thinking skills with a proven ability to walk onto a client site, unpack a highly ambiguous data landscape, and execute a structured path toward production code