Software Engineer

Software Engineer

The Alaka`ina Foundation Family of Companies (FOCs) is looking for a qualified Software Engineer to support our government customer located at Kirtland Air Force Base in Albuquerque, New Mexico. Are you a data scientist that wants to explore some problems in natural language processing, image, and/or video analysis? To clean, process, analyze, and learn on exotic data to your heart's content? We've got millions of documents that need to be digitized, OCRed, and analyzed using machine learning for information like, titles, authors, etc. but we also want to automatically extract and create time-series data from pictures of graphs! Plus, we fully endorse exploration of transformer models to semantic reasoning over this textual data. Not cool enough, you say? Alright, well what about automatic quantification of data from video productions and event detection? Getting warmer? What about automatic film summarization? Image summarization? Automatic captioning of events? It's not just the analysis, but the searching too, so we'd like you to be able to identify methods to facilitate searches over the cool analyses you've done so it can be found by others. Plus there's all the background stuff, like building good, commented, and maintainable code. One-off projects like little scripts to take care of little things that will inevitably come our way. Are you a solid python programmer, with an understanding of libraries like pandas, scikit, tesseract, pytorch, or tensorflow? Do you know some of these libraries but maybe not others, and you'd like to learn them all? What about Javascript? Does some front-end UI development sound interesting? This job is a playground for cool AI ideas you can come up with that involves analyzing text, image, and video data, along with development of a large software project.

The primary mission of the Defense Threat Reduction Information Analysis Center (DTRIAC) is to provide timely electronic access to all nuclear weapons test data, legacy and current, to U.S. government programs supporting U.S. nuclear deterrent missions. DTRIAC maintains a repository of over 20,000 films, two million photographs, and 60 million pages of documents dating back to The Manhattan Project. Kāpili Services is charged with making the above hardcopy materials easily accessible to DTRA deterrent mission researchers in a way that provides knowledge and meaning through the use of digitization, Machine Learning (ML), Artificial Intelligence (AI), and data science. The Software Engineer/Developer works within a team of software engineers, data scientists and application architects to apply Optical Character Recognition (OCR), Machine Learning (ML), and Artificial Intelligence (AI) to search and/or organize and characterize a digital archive collection and develop improvements to the user interface and searchability of the archive.

Desired Degree/Education/Certification

Master's degree in relevant field (e.g. Comp Sci, Math) Ability to obtain CompTIA Security+ Certification

Required Skills And Experience

Four plus (4+) years relevant experience; Two plus (2+) years with relevant degree (e.g. Comp Sci, Math) Python experience with machine learning libraries (e.g. scikit, tensorflow, etc) A desire to learn Javascript to communicate results on the front-end You've got skills in at least one of NLP, image analysis, or video analysis, and would like to expand your knowledge into all of these areas Cleaning noisy data, anomaly detection, imputation of missing values, etc. Practical experience and knowledge of machine learning and statistical modeling

Desired Skills And Experience

Ability to translate research papers into actionable machine learning algorithms Experience/Proficiency with utilizing Tesseract OCR and OpenCV with Python Familiarity with the ELK stack Experience in developing and implementing CNNs, RNNs, and Transformer models Experience with computer vision and image processing analyses Experience with any of the following tools:SAS, Apache Hadoop, Tableau, TensorFlow, BigML, Knime, RapidMiner, Apache Flink, DataRobot, Apache Spark, MongoDB, Trifacta, Minitab, Apache Kafka, QlikView, Julia, SPSS, Keras, Matplotlib, Pytorch, scikit-learn, Weka, Domino Data Science Platform, IBM Watson Studio.

Required Citizenship And Clearance

Must be a U.S. Citizen. Ability to obtain and maintain a Top Secret Clearance Required