Senior Data Scientist
Employment Type: Full-Time
Genentech's Early Clinical Development (ECD) department is looking for a Senior Data Scientist with a passion to provide predictive analytics solutions and insights. The data scientist reports to the lead of gRED Predictive Analytics (gPA). The gPA group supports Clinical Operations study teams and management by applying business intelligence, data science, predictive analytics, and operational analytics to make informed data driven decisions in operational execution of a clinical trial.
The ideal Senior Data Scientist has a high degree of expertise to establish and leverage advanced analytics solutions and apply novel AI/ML data science and predictive analytics methods to drive operational efficiencies of clinical trials. The Sr. Data Scientist is responsible for the research, design, development, validation, implementation and deployment of machine learning and statistical modeling solutions to challenge various business issues in early research and early clinical development, which significantly contribute to the advancement of Genentech's drug development pipeline.
* Lead key ML data science projects to ensure successful completion and develop plans to integrate capabilities into existing early clinical development process
* Influence the development, and delivery of advanced analytics goals in alignment with gRED and ECD's strategic goals and priorities
* Ability to work independently with cross functional multi-disciplinary teams to solve challenging business problems
* Application of data science, machine learning and optimization methods that inform the operational execution of a trial (speed, efficiency, cost) for planned and active trials which are tailored to unique protocol inputs and drivers
* Deliver analytics that proactively identify areas of risk and provide trial teams with predictive risk indicators and assist with mitigations
* Execute machine learning lifecycle from ideation and hypothesis generation, data extraction and exploration, model building and validation, results communication, and productization
* Possess in-depth knowledge of real-world data assets, evaluate emerging datasets and technologies that may contribute to existing analytical platforms
* Prepare reports and documentation surrounding projects
* Promote collaboration with other data science teams within gRED and cross-Roche, encourage reuse of artifacts.
* Train colleagues on basic data science principles and techniques
* Keep abreast of the latest developments in the Data Science field by continuous learning and proactively champion promising new methods relevant to the problems at hand
Qualification / Experience
* 5+ years' experience with designing, developing, maintaining and performing data analysis (predictive analytics, machine learning, operations research) to support business needs
* Substantial experience in solving machine learning, statistical modeling, and/or data science problems covering areas such as supervised/unsupervised learning, ensembles, time-series data analysis, forecasting modeling, neural networks, NLP, Monte Carlo and other simulation techniques
* Knowledge of the pharmaceutical/biotech clinical development process is highly preferred
* Excellent written and verbal communication skills which contribute to a strong, collaborative team-oriented environment
* A Master's or PhD degree from an accredited college or university with major course work in Data Science, Computer Science, Operations Research, Statistics, Mathematics, Bioinformatics, Computational Neuroscience/Biology or related field is required
* Equivalent work experience in a similar position may be substituted for educational requirements
* Candidates must have a specialization in ML, AI, or data science.
* 5+ years' experience in data access, and programming languages including SQL, PL/SQL
* Proficiency in one or more programming skills such as Python, R, PySpark, TensorFlow, Pandas, Numpy, Scikit Learn and PyTorch
* Experience with statistical tools (Jupyter Notebooks, AutoML, Pandas, Spark MLlib, R, SciPy, etc.)
* At Least 5 years' experience with Data Mining, Predictive Modeling, Machine Learning, AI (Regression, ANN, Decision Trees, Clustering), Text Mining, Sentiment Analysis, Forecasting, Simulation, Optimization, Experimental Design
* Experience with data visualization tools such as Looker, Data Studio,Tableau, Power BI, etc.