# Alissa Ostapenko > Software Engineer at Amazon Robotics Location: Greater Boston, United States Profile: https://flows.cv/alissaostapenko Computer science graduate student interested in multilingual natural language processing (NLP), cultural analytics, and ethics and fairness of NLP technologies. ## Work Experience ### Software Development Engineer II @ Amazon Fulfillment Technologies & Robotics Jan 2024 – Present | Boston, Massachusetts, United States ### Software Engineer @ Amazon Fulfillment Technologies & Robotics Jan 2022 – Jan 2024 | Boston, Massachusetts, United States Building software solutions for customers across Amazon Robotics. ### Graduate Research Assistant @ Carnegie Mellon University School of Computer Science Jan 2020 – Jan 2022 | Pittsburgh, Pennsylvania, United States Developed person-aware Natural Language Processing tools, specifically to handle code-switched (mixed-language) text (Adv. Dr. Yulia Tsvetkov, University of Washington) Main projects: (1) Developed an adaptable, user-informed model to predict code-switch (language switch) points in mixed English-Spanish dialogues. I presented our work at ACL 2022 in Dublin. In the future we see this classifier implemented into an adaptable dialogue system to control switches between languages. (2) Using statistical techniques to analyze psycholinguistic drivers of code-switching. There are several existing hypotheses for why people switch languages. Our goal is to identify when each hypothesis is most relevant to categorize different types of code-switch points. Key Tools/Frameworks: PyTorch, Pytorch Lightning, statsmodels ### Software Engineer, Manufacturing Division @ Amazon Robotics Jan 2020 – Jan 2020 | North Reading, Massachusetts, United States • Using stakeholder feedback, iteratively implemented data processing pipelines and dashboards illustrating real-time test performance stats of robotic drive units used in Amazon fulfillment centers (AWS tools: Athena, S3, Lambda, DynamoDB) • Employed statistical techniques to identify historical patterns in test data from different drive unit components and to help flag suspicious behavior from new drive units before they are shipped for production ### Cognitive Software Engineering Intern @ State Street Jan 2019 – Jan 2019 Implemented core services for the company-internal Voice to Text portal for transcribing and analyzing uploaded videos and audio: • Developed modular S3 data storage service using Flask. Service could be integrated with any of the team’s AI-driven tools for efficient, reliable, and persistent data storage on Amazon’s S3 cloud. • Developed Flask-based orchestration service to integrate Dockerized voice to stext service with S3 data storage service. Used PostgreSQL database to track metadata of uploaded documents and service output results. • Experimented with pre-trained voice-to-text model using Kaldi. Researched techniques for unsupervised content classification of transcribed audio to extend the capabilities and usefulness of the voice-to-text service. ### Data Research Analyst @ Vestigo Ventures Jan 2019 – Jan 2019 | Cambridge, Massachusetts Towards Machine Learning-Driven Financial Website Classification, adv. Dr. Rodica Neamtu • Worked closely with an analyst from Vestigo Ventures to develop an extensible tool (“FinDX”) for classifying a company’s business domain as FinTech/non-FinTech from its website (Python 3, NLTK, spaCy). • Implemented a novel keyword-driven website crawler for extracting text from a company’s website. • Performed extensive experimentation with part-of-speech and ontology-based text extraction techniques using a real-world, proprietary dataset and a large, public dataset of Business websites. • Wrote a script to easily train and test a website classifier on a custom business domain and dataset. ### Undergraduate Research Assistant @ Worcester Polytechnic Institute Jan 2019 – Jan 2019 | Worcester, MA Intoxication Detection from Audio Using Deep Learning, adv. Dr. Emmanuel Agu • Employed CNN-based techniques to classify sober and intoxicated speech in the Alcohol Language Corpus (ALC). • Developed the core audio feature extraction script for my team members to extend (Python 3). • Designed and implemented a full pipeline for training and evaluating our CNN models (keras). ### Undergraduate Student Researcher @ Johns Hopkins Whiting School of Engineering Jan 2018 – Jan 2018 | Baltimore, Maryland Area • Extended a deep, multi-modal machine translation model to translate a caption given the caption’s text and its associated image using attention mechanisms (PyTorch). • Performed extensive experimentation into different attention mechanism techniques. • Wrote a script to qualitatively evaluate image-text associations produced at model test time (Python 3). • Presented research at a final presentation to industry sponsors including Google, Facebook, & Microsoft. ### Research Assistant Intern @ Newmetrix Jan 2017 – Jan 2017 | Cambridge, Massachusetts • Performed data analysis and ran experiments to collect and process data using Amazon Turk (AWS). • Built multilayer perceptron classification models to identify and label target objects in an image (scikit-learn). Code was officially submitted into the company codebase. • Utilized image processing techniques to analyze and label image data (Python 3, PIL) for training models and for evaluating their performance. • Wrote a script to qualitatively analyze object classification performance and presented results in biweekly Scrum meetings. ## Education ### Master's in Language Technologies (Computer Science) Carnegie Mellon University ### Bachelor of Science - BS in Mathematics and Computer Science Worcester Polytechnic Institute ## Contact & Social - LinkedIn: https://linkedin.com/in/alissaostapenko --- Source: https://flows.cv/alissaostapenko JSON Resume: https://flows.cv/alissaostapenko/resume.json Last updated: 2026-03-31