Manufacturing - Post-Doctoral Research Scientist

Postdoctoral Fellow - Natural Language Processing (NLP) and Artificial Intelligence (AI)

Responsibilities:

• Utilizes supervised or unsupervised methods, learning from vast amounts of unlabeled data to drive insight from unstructured text
• Ensures life cycle management of code is maintained through version control and associated repositories.
• Develops high quality analytical and statistical models, insights, patterns, visualizations, that can be used to improve decision making in manufacturing operations.
• Responsible for documentation of all technical work both within and outside of formal document management systems
• Independently develops code and analytical models to automate data transformation and analysis
• Performs data engineering, preprocessing, exploratory data analysis, and model development by interacting with a variety of databases
• Responsible for ingestion, integration and delivery of data across multiple platforms
• Works to maintain and uphold data integrity and clean data principles
• Communicates with team members regularly to provide updates and collaborate on deliverables.
• Displays a high level of teamwork and collaboration both within and across functions

Requirements:

• PhD with knowledge of deep learning methods for NLP (quantitative area of study, Computer Science, preferred)
• Strong background and demonstrable experience in Natural Language Processing and Computational Linguistics is required
• Proficient in writing and developing analytical and machine learning models using python modules including pandas, numpy, scikitlearn, and tensorflow. Experiencing developing and implementing MLOps pipelines.
• Experience building analytical and statistical models to answer key business questions
• Experience using git via the command line
• Strong understanding of core statistical concepts to solve real world problems
• Intermediate to advanced proficiency (3+ years post academia experience as an independent contributor designing and delivering data solutions) in SQL.
• Experience interacting with various data warehouses and large-scale, complex datasets using ETL and BI tools and platforms.
• Self-motivated to identify and propose Client methodologies that will drive increased efficiency
• Demonstrate expert knowledge in machine learning and rule-based systems as applied to computational linguistics and natural language processing, as well as development and execution of annotation tasks with teams of experts
• Proficiency in mathematics with the skill to translate complex mathematical algorithms into usable computational methods
• Experience with data mining and analysis techniques across disparate data sources
• Experience working in LINUX/UNIX environments
• Experience interacting with PostgresSQL, Oracle, Impala Cloudera, Okera or similar databases
• Experience with JupyterLabs, Anaconda, and RStudio
• Intermediate proficiency with python
• Experience developing visualizations using a variety of methods (plotly, matplotlib, seaborn)
• Experience working within Domino Data Lab projects
• Technical knowledge of performance tuning and query optimization across large data sets.
• Experience with data cataloguing and enablement through APIs
• Experience with a variety of computer science languages (C++, Java, html/css)
• Exposure to bioprocess engineering/cell therapy data
• Knowledge of GxP requirements (preferably related to data and code management)

Preferred:

• Dashboard development experience (Tableau, Spotfire, DASH)
• Experience working with the pharmaceutical industry