Skills
• Machine learning
• Backend development
Programming Languages
Python C++ Java Typescript
Education
MS in Machine Learning at Técnico Lisboa (2019 - now)
BS in Computer Science at AUA (2015 - 2019)
AYB High School (2012 - 2015)
Tools, APIs, Libraries
General:
• Git, Jira
• Docker, Docker-Compose
• Travis CI

Machine Learning:
• Tensorflow 2, Keras
• Pytorch, Pytorch Lightning
• Pytorch Geometric
• Keras Applications, Keras tuner, baytune
• SciPy, spaCy, nltk, huggingface-transformers

Backend:
• gRPC, Protobuf
• Swagger
• ElasticSearch
• PostgreSQL, MySQL
• Flask, Django, Django REST framework
• Gunicorn
• Firebase, Heroku

Hobbies
Football Basketball Travel Break Dance
Experience
Current Projects
Approximating Betweenness-Centrality with Graph Neural Networks:
Approximation of betweenness-centrality metric for graphs using graph neural networks.
Technologies used: Pytorch, Pytorch Lightning, Pytorch Geometric

Predicting Resolution from Satellite Imagery:
New benchmark for predicting resolution given a satellite image using contrastive learning. The collected dataset consists of a sample of several open-source datasets.
Technologies used: Tensorflow 2, Keras
2020 - 2021
Machine Learning
ML Researcher at YerevaNN
DIIN in Keras - [Arxiv Report]
Within the scope of the ICLR Reproducibility challenge, published a report on reproducibility of a DIIN neural network architecture for natural language inference using Keras.

R-Net in Keras - [Blogpost]:
Keras implementation of the complex neural network called R-net designed by Microsoft Research for question answering. Published a blog post on the implementation details and reproducibility of the R-Net paper

word2morph2vec - [Paper] - University capstone project
Developed an end-to-end pipeline for extracting "linguistically accurate" morphological vectors for given words or sentences. The system is based on FastText and COMBO. Experiments are tested and evaluated on the Russian language.
2017 July - 2019 Sep
Toptal
ML Freelance
NLP Engineer at Omni
Worked in a startup team to create and deploy NLP services to production on AWS which included:
• Semantic search service on top of solutions from MS-MARCO competition and ElasticSearch.
• Automatic suggestion service using extractive summarization based on BERT.

Technologies used:
• NLP - TensorFlow, HuggingFace Transformers, ElasticSearch
• Deployment - Flask, AWS, Docker, Kubernetes, GitHub Actions
2020 March - 2020 April
Facebook Internship
Full Stack Development internship
Worked on internal tool for monitoring the viewability of advertisements (Ad measurement team)

Technologies used:
• Front-end - React.js, Redux, TypeScript - UI of the tool
• Back-end - Hack - DB queries and logic of the tool
• Machine learning - Python FBLearner - Predict ad-viewability score
2018 Summer

Infra/Networking internship
Worked on an open source project called Magma which aims to give network providers a mobile network core solution

Technologies used:
• Python - Ryu SDN framework, python-fire, Scapy
• C++ - glog, spdlog
• General - gRPC, Protobuf, Open vSwitch, Swagger, Wireshark, Vagrant
2019 Summer