# Catalin Tiseanu > Machine learning leader at Coinbase. Productionized Transformers before they were cool Location: United States, United States Profile: https://flows.cv/catalin I'm passionate about technology that solves real problems, with focus for algorithmic, optimization, or machine learning challenges, proven to perform under pressure. I have a heavy background in algorithms & data structures, and machine learning - I worked at Coinbase, Twitter, Facebook, Google, and IBM Research, and won or made the final at some of the most prominent programming contests in the world, such as Google Code Jam or TopCoder Open (whose Marathon track I won in 2021 against heavy competition). Most recently, I was the first ML Engineer at Coinbase, acting as the team's tech lead for the last three years over a 40+ team. I had a role in building, designing, or advising every ML model running in production currently at Coinbase, as well as the technical and strategic direction. Highlights: • Landed double-digit increases in site-wide net revenue and engagement across the Feed, Growth & Notifications, and user spend limits; • Created Auto-ML-like lego-blocks around tabular data, sequence & text data (using Transformers of ChatGPT fame & deep learning), and support for blending these models to help 10x the team; • Set long-term technical direction for the team owned large parts of the interview process, published a blog post around our stack, contributed to a KDD presentation, and ran a knowledge-sharing group and boot camp; • Worked on the first web3 use cases. I was a founding engineer at Memo.ai (acquired by Coinbase), working on various NLP tasks. Previously, I did big data work at BitDefender and got my first industry experience through internships at Google (2008), Facebook (2010), and Twitter (2012). I published several theoretical computer science papers in string algorithms and strand detection, with an h-index of 4. I also built the first real-time turnout electoral map for the Romanian parliamentary elections, used by more than 1% of the Romanian voting population. I have Research Master's degree in Computer Science from the University of Maryland, College Park, under Prof. Mohammad HajiAghayi, and a Bachelor's degree in Computer Science from the University of Bucharest, Faculty of Mathematics and Informatics. To find out more about me, visit https://catalintiseanu.github.io/ ## Work Experience ### Senior Staff Machine Learning Engineer (IC7) @ Coinbase Jan 2022 – Present | San Francisco Bay Area As the first ML Engineer, I co-founded the modern machine learning efforts at Coinbase, acting as the team's tech lead for the last three years over a 40+ team. I had a role in building, designing, or advising every ML model running in production currently at Coinbase, as well as the technical and strategic direction. Highlights: * Landed double-digit increases in site-wide net revenue and engagement across the Feed, Growth & Notifications, and user spend limits; strategic independence of 3rd-party vendors and a massive reduction in fraud for the ATO & Risk domain; and improving support agent response time. * Created Auto-ML-like lego-blocks around tabular data, sequence & text data (using Transformers - the T in ChatGPT - from scratch & deep learning), and support for blending these models. Machine learning engineers and data scientists across the company use these lego-blocks to deliver impact. * Set long-term technical direction for the team, owned large parts of the interview process, published a blog post around our stack, contributed to a KDD presentation, and ran a knowledge-sharing group and boot camp. * Proposed a Responsible AI framework around model cards inspired by academia, which is used by new models. * Working on the first ML + Crypto use cases. ### Staff Machine Learning Engineer @ Coinbase Jan 2018 – Jan 2022 | San Francisco ### Founding Engineer @ Alien Labs Jan 2016 – Jan 2018 | San Francisco Bay Area Worked on applying NLP on Slack chat logs - expert finding, topic modeling, text classification. Improved search quality. Later on, built full-stack features such as web search and external note sharing. Machine learning =============== Expert finding: • Tf-idf based model for recommending experts based on a query string Topic modeling: • Pipeline for cleaning text data, parsing out stop-words and first names, keeping only nouns • Langid-based classifier for keeping only english-speaking teams • Clustered the cleaned-up text messages using LDA in 50 clusters * Visualized results using pyLDAvis Text classification: • Collected a labeled dataset for classifying messages into design/non-design • Built additional filtering step for design-messages using a vocabulary from design-related Wikipedia pages • Used fastText as an initial baseline (both with pretrained Glove word vectors and with training the word vectors). Got 0.83 f1-score • Reproduced colleagues Bidirectional LSTM classifier using Keras. Got 0.86 f1-score Technologies used: jupyter, pandas, fasttext (text classification), gensim (lda), keras (bidirectional LSTM) Search quality ============ • Collected gold dataset of queries and expected positives for those queries • Built search quality eval tool • Iterated on the ElasticSearch model • Improvement top3 recall from an initial 30% to 90% for that gold dataset * Had follow-up call with an ElasticSearch outside expert consultant Full-stack ======== • Web-search • External note sharing (via public link) • Invite flow • Note Reactions (similar to the Facebook ones) Technologies used: Python, React, CSS, HTML ### Big Data Arhitect @ Bitdefender Jan 2015 – Jan 2016 | Bucharest * In charge of building the big data system in charge of making sense of terabytes of diverse information * Worked on building a one box type of search system for the various data collected by BitDefender, using Cassandra, Spark and Django. * Aim of the system was two-fold: easily search through terabytes of data and automatically generate forensic leads for the analysts to investigate. ### Teaching Assistant @ University of Maryland Jan 2011 – Jan 2013 | College Park * TA for Algorithms & Data Structures, Complexity Theory and Randomized Algorithms * Held weekly TA hours for explaining difficult course material, at both undergrad and grad level * Responsibilities also included grading homework ### Software Engineering Intern @ Twitter Jan 2012 – Jan 2012 | San Francisco * Shipped a drastically improved version of the signup account recommendation system. * Designed and implemented features for improving the experience new users have on the site, by suggesting more relevant accounts to follow after they just signed up. * The project relied heavily on understanding trends in big data. * To that end, I used Pig (Big Data) and Scala (Backend). * I used one of the features as part of a Hackweek project, which ended winning one of the top prizes. ### Software Engineering Intern @ Facebook Jan 2010 – Jan 2010 | Palo Alto * Worked in the Ads optimization team. * Implemented a feature which helped increase CTR ... this needed both infrastructure work as well as some Machine Learning models, all coded in C++. * Implemented a text feature as a Hackathon project to help make indexing easier. * I also used Big Data technologies such as Hive. ### Great Minds Research Intern @ IBM Research Zurich Jan 2010 – Jan 2010 | Zurich * Interned in the Business Optimization group on a research project about risk management in the pharmaceutics industry. * Worked on the interface of stochastic programming and combinatorial algorithms in order to formulate a model which minimized risk. * The linear programming model was implemented in ILOG CPLEX C++ and compared against other methods. * The joint results of this work were published in the Operations Research Proceedings 2010. ### Software Engineering Intern @ Google Jan 2008 – Jan 2008 | Mountain View * Worked on the Google Books team. * Implemented an user facing feature as well as a backend one related to the scanning of books * Used Python for prototyping and C++ for the code in production. ## Education ### Research Master in Computer Science University of Maryland Jan 2011 – Jan 2013 ### Masters in Computer Science University of Bucharest Jan 2009 – Jan 2011 ### Bachelor in Computer Science University of Bucharest Jan 2006 – Jan 2009 ## Contact & Social - LinkedIn: https://linkedin.com/in/catalintiseanu - Website: https://catalintiseanu.github.io/ --- Source: https://flows.cv/catalin JSON Resume: https://flows.cv/catalin/resume.json Last updated: 2026-03-22