Computational Scientist, Machine Learning
Posted on Apr 5, 2021 by Pfizer
The Pfizer Simulation and Modeling Sciences (SMS) group has an opening for a computational methods developer with strong expertise in computational biology, bioinformatics, Artificial Intelligence (AI) and Machine Learning (ML). Working with the biotherapeutics group, the successful candidate will leverage skills in sequence analysis, protein structure modeling, machine learning, and scientific programming to develop AI models and computational tools that enable design of antibody therapeutics and prediction of biophysical and therapeutic properties. To be successful in this role, the incumbent must be able to effectively collaborate with colleagues with diverse scientific background, identify problems and opportunities, and combine techniques from computational biology and AI, in particular recent advances in deep learning, to rapidly develop powerful computational solutions.
Identify novel and creative applications of deep learning approaches to advance discovery and development of antibody therapeutics.
Collaborate across biotherapeutics organization to implement powerful AI models and cutting-edge computational tools to enable rapid developability assessment of novel monoclonal antibodies.
Effectively utilize relevant public and proprietary databases and available computational resources (internal HPC and Cloud) to develop ML models to predict important biophysical and therapeutic properties of antibodies.
Occasionally contribute to the ongoing and new ML-related efforts within SMS in the area of small molecule discovery and development.
Leverage proprietary computational framework and applications to deploy AI/ML models for wide usage by Pfizer scientists.
Proactively identify, assess, and internalize promising methods and tools.
Communicate and explain computational models and ML techniques to broad scientific audience from diverse discipline.
Ph.D. in computational biology, chemical engineering, computer science, physical or biological sciences, machine learning, or related discipline.
Experience with several machine learning algorithms (eg Random Forest, Support Vector Machine, Deep Neural Networks) and packages (eg Sci-kit Learn, Keras, TensorFlow, PyTorch).
Track record of applying machine learning, in particular modern deep learning approaches, to solve relevant biological problems.
Familiarity with concepts, techniques, and common tools used for sequence analysis and protein structure modeling.
Experience with Unix/Linux, HPC environments, and high-level programming language (eg Python).
Excellent communication and interpersonal skills.
Demonstrated track record of applying AI/ML, in particular cutting-edge deep learning techniques such as ConvNet, RNN, generative modeling, and reinforcement learning to tackle complex drug discovery and development problems.
Experience in applying ML to immunology data, eg HLA peptide binding