Lead Machine Learning Engineer, adMarketplace

• PhD with 5+ years of experience or MS with 5-8+ years of industry experience in AI/ML, developing and deploying production-grade ML systems
• 2+ years of experience in building AI/ML models in at least one of the following domains: Ads, relevance, ranking, recommendation systems, and search
• 3+ years of experience in building distributed, low-latency, high-throughput batch and online ML services
• 3+ years of experience in deploying and maintaining ML pipelines in production, including feature engineering and model monitoring frameworks
• 2+ years of experience in Python and proficiency with distributed frameworks (Spark, Hadoop), SQL, and cloud infrastructure
• 2+ years of experience with ML packages such as Tensorflow or PyTorch, scikit-learn, and Spark ML
• Ability to operate efficiently in a high-paced, multi-functional, and rapidly evolving environment

Desirable

• We are seeking an experienced Lead Machine Learning Engineer passionate about building impactful products in the search and advertising technology ecosystem
• As part of our established AI/ML and Search organization, you will be instrumental in developing and optimizing advanced models and applications to enhance our ultra-low-latency ad-serving platform and consumer-facing search solutions
• You will collaborate closely with product, business, and other engineering teams, making significant contributions to strategic initiatives such as relevancy & yield optimization, predictive modeling, and improved bidding performance
• You will have a clear career progression path and numerous opportunities for both personal and professional growth in an intellectually stimulating and dynamic work environment
• Drive end-to-end lifecycle management of AI/ML projects from concept and data acquisition to prototyping, model development, deployment, optimization and ongoing maintenance
• Implement and champion best practices in MLOps, including data collection, model training pipelines, model deployments, monitoring, alerting, and QA to ensure model reliability and performance
• Contribute significantly to model architecture decisions, leveraging state-of-the-art machine learning, deep learning, and reinforcement learning techniques
• Develop and deploy robust feature engineering pipelines and ML services optimized for low latency and high throughput
• Establish and utilize robust A/B testing and experimentation frameworks to evaluate and iteratively improve model performance
• Translate research papers into high-quality, production-ready code
• Communicate effectively, collaborate, and build long-term relationships across the organization
• Mentor junior team members in achieving engineering excellence and be a change agent on the team