Artificial Intelligence Engineer, Natural Language Processing
Overview
Verantos (https://verantos.com) is a market leader in high accuracy real-world evidence (RWE) generation. The Verantos RWE platform integrates heterogenous real world data sources and generates evidence with the accuracy necessary for regulatory and reimbursement use. The Verantos RWE platform leverages data science and artificial intelligence along with advanced data sources such as electronic health records (EHR) to generate RWE capable of supporting complex clinical studies. Some of the largest biopharma companies in the world are Verantos customers.
We are looking for a natural language processing (NLP) engineer to join the AI team to scale up the AI components of Verantos’s solution. This position will be responsible for working with the Product Manager to drive the NLP strategy and building out all the NLP models and infrastructure.
The ideal candidate will be passionate about health care, software engineering, machine learning and stay up-to-date with the latest developments in the field.
Responsibilities
Understand business objectives and develop models that help to achieve them, along with metrics to track their progress
Articulate experiment plans that demonstrate the process of model building, refinement and productization
Manage available resources such as compute, data, and personnel so that deadlines are met
Analyze algorithms that could be used to solve a given problem and ranking them by their success probability
Explore and visualize data to gain an understanding of it, then identify differences in data distribution that could affect performance when deploying the model in the real world
Verify data quality, and/or ensure it via data cleaning
Supervise the data acquisition process if more data is needed
Find available datasets online that could be used for training
Define validation strategies
Define the preprocessing or feature engineering to be done on a given dataset
Define data augmentation strategies
Train models and tuning their hyperparameters
Analyze the errors of the model and design strategies to overcome them
Deploy models to production
Present model outcomes in a scientifically rigorous manner
Qualifications
Bachelor’s degree in engineering, math or science from a reputed institution (graduate degree strongly preferred)
3+ years working as a NLP engineer
Proficiency with a deep learning framework such as TensorFlow
Experience building production-ready NLP systems, from preprocessing and normalization to monitoring model drift in a production environment, ideally using NLP libraries and technologies including Spacy, PyTorch & Deep Learning models
Proficiency in leveraging cloud-based machine learning resources such as those from Amazon Web Services or Google Cloud for model training and productization
Expertise in visualizing and manipulating big unstructured datasets