Project Description:
The project focuses on designing and building machine learning systems for search ranking and personalized recommendations at scale.
Project Phase:
ongoing
Soft Skills:
• Ability to influence teammates and cross-functional stakeholders effectively.
• Curious and improvement-oriented mindset with a willingness to challenge existing approaches.
• Excellent ability to communicate complex technical concepts and results with clarity.
Hard Skills / Must Have:
• 5+ years of machine learning engineering experience.
• Experience with search, NLP, ranking, recommendation, or relevance systems.
• Expert-level Python and its core data science libraries and SQL (e.g., PySpark, Pandas, NumPy, Scikit-learn, PyTorch)
• Ability to design an ML system from scratch, including data analysis, annotation, processing, and production serving.
• Experience translating business goals into ML objectives with appropriate proxy metrics and non-functional requirements.
• Experience designing and evaluating online experiments with statistical validation.
• Experience with MLOps tools and practices.
• Experience deploying ML models to production with latency optimization.
• Knowledge of concept drift detection and management.
Hard Skills / Nice to Have (Optional):
• Academic background in Computer Science, Mathematics, or another quantitative discipline.
• Experience fine-tuning and deploying large or small language models for query understanding or relevance.
• Experience with search relevance and autocomplete systems.
• Experience with mapping, location, or geospatial products.
• Experience building products for developing markets.
• Experience with cloud data and machine learning platforms.
• Deep expertise in search, ranking, recommendation, or geocoding systems.
Responsibilities:
• Design and build deep learning systems for search ranking, personalized recommendations, and session-based recommendation engines.
• Integrate geographic context into ranking systems and improve pickup point recommendations.
• Translate business objectives into machine learning objectives with appropriate non-functional requirements.
• Lead model evaluation using offline metrics and online experiments.
• Collaborate with backend engineers to deploy production-ready low-latency ML models.
• Work closely with product managers and operations teams to transform behavioral insights into product features.
• Own the end-to-end production ML lifecycle, including serving, monitoring, drift detection, and retraining pipelines.
Technology Stack:PySpark, Pandas, NumPy, Scikit-learn, PyTorch, BigQuery, Databricks