(Senior) Scientist, Machine Learning (Active Learning & Bayesian Optimization) | Cambridge, Massachusetts, United States | Flagship Pioneering, Inc.

Position:	(Senior) Scientist, Machine Learning (Active Learning & Bayesian Optimization)
Institution:	Flagship Pioneering, Inc.
Location:	Cambridge, Massachusetts, United States
Duties:	Design, build and scale supervised ML models for active learning and Bayesian Optimization of materials synthesis and performance; Implement best practices and innovate methods for uncertainty quantification; Combine datasets of multiple fidelities and sources to power data-driven materials discovery; Work with the computational team to identify materials design pathways that target desired functional properties and their synthesis; Work with infrastructure and automation teams to transfer data and predictions in real time; Work with the experimental team to drive material discovery and development, and build domain-specific acquisition functions
Requirements:	PhD in Computer Science, Applied Mathematics, quantitative disciplines with strong focus in ML, or related field; Experience with uncertainty quantification, active learning and Bayesian Optimization; Experience implementing, evaluating, and hyperparameter tuning small and large supervised models in a Bayesian Optimization context (Gaussian processes, Bayesian Neural Networks) on small and large datasets; Strong experience in at least one ML framework (PyTorch/TensorFlow/Jax) and robust experience in Python data science ecosystem (Numpy, SciPy, Pandas, etc.); Experience using a cloud computing service to reduce runtime to train and evaluate deep learning models

Text:	(Senior) Scientist, Machine Learning (Active Learning & Bayesian Optimization) Design, build and scale supervised ML models for active learning and Bayesian Optimization of materials synthesis and performance; Implement best practices and innovate methods for uncertainty quantification; Combine datasets of multiple fidelities and sources to power data-driven materials discovery; Work with the computational team to identify materials design pathways that target desired functional properties and their synthesis; Work with infrastructure and automation teams to transfer data and predictions in real time; Work with the experimental team to drive material discovery and development, and build domain-specific acquisition functions PhD in Computer Science, Applied Mathematics, quantitative disciplines with strong focus in ML, or related field; Experience with uncertainty quantification, active learning and Bayesian Optimization; Experience implementing, evaluating, and hyperparameter tuning small and large supervised models in a Bayesian Optimization context (Gaussian processes, Bayesian Neural Networks) on small and large datasets; Strong experience in at least one ML framework (PyTorch/TensorFlow/Jax) and robust experience in Python data science ecosystem (Numpy, SciPy, Pandas, etc.); Experience using a cloud computing service to reduce runtime to train and evaluate deep learning models