Data Science Lead

As a Lead Data Scientist at Blend, you will be at the forefront of developing advanced recommendation engines and deploying sophisticated machine learning models into production environments. Your expertise in Python and PySpark coding, combined with practical experience in MLOps, will be crucial in enhancing our data-driven decision-making processes. You will design and implement scalable machine learning pipelines, emphasizing production-grade reliability and performance. Collaboration with data engineering and product teams will be essential in translating complex business requirements into actionable ML solutions within the Databricks environment. You will also lead the end-to-end development of machine learning models, from experimentation and training to deployment, monitoring, and retraining, while adhering to MLOps best practices. Optimizing model training and inference workflows using distributed computing in Databricks will ensure efficient resource usage and minimal latency. In-depth performance evaluations and validation strategies are essential for ensuring robustness and fairness of models in production. Maintaining high standards in reproducibility and traceability by leveraging the experiment tracking and lineage features in Databricks will be a key responsibility. Your role will also involve partnering with stakeholders across business units to align modeling efforts with strategic objectives, ensuring impact and scalability of ML-driven initiatives.