Candidate will implement the inference infrastructure to do a pilot testing the feasibility and scalability of a new machine learning algorithm to identify the author of small to large portions of text. The infrastructure to do the training has already been implemented. The candidate will build the infrastructure to coalesce the appropriate data, apply the model to the collected data, and store the results into an Accumulo table that will be queried by the end user system. The candidate will work closely with the researchers who developed the algorithm and the developers of the end user system. If time permits the candidate might be required to accelerate the training and inference of the machine learning algorithms using GPU accelerated machine learning APIs.