Maria Obedkova | NLP Engineer 👩💻
NLP/AI Engineer with 5+ years of industry experience with
Machine Learning and Large Language Models, backed by
a strong linguistics background. Skilled in developing
diverse NLP and AI applications, with a passion for
advancing AI, building impactful products, and enhancing
human-computer interaction.
🔗 Important Links
👔 Experience
Senior NLP Engineer at TrustYou
Sep 2022 - present | remote and Munich, Germany
ML - LLMs - ABSA - GenAI - CI/CD - MLOps - RAG - BERT - GPT - Python - PyTorch - HuggingFace Transformers - LangChain - MLFlow
- Working on GenAI solutions and their improvement lifecycle
- Improving a Transformer-based solution for ABSA, scaling it up for multiple languages and bigger review load
- Defining system designs for ML and DL applications
Apr 2020 - Aug 2022 | remote and Munich, Germany
ML - LLMs - ABSA - CI/CD - BERT - GPT - Python - PyTorch - HuggingFace Transformers - MLFlow - CFG
- Developed a Transformer-based solution for ABSA and put it in production
- Researched approaches to ABSA and performed data analyses
- Supported and maintained the legacy system that performed sentiment analysis using CFG
Feb 2019 - Jul 2019 | Stuttgart, Germany
ASR - AWE - DL - Python - TensorFlow - Java - Kaldi
- Researched different deep learning approaches to pronunciation generation for speech recognition
- Investigated Acoustic Word Embeddings and improved their quality for a pronunciation discrimination task
- Developed a completely new data-driven method of pronunciation generation for ASR purposes
NLP Engineer at Fact Read
Oct 2016 - Dec 2018 | remote
Fact Extraction - Coreference Resolution - WSD - ML - Python - scikit-learn
- Implemented the morphological-syntactical pipeline and improved its quality
- Developed the anaphora resolution module for news texts using a machine learning approach
- Supervised linguists and coordinated the interaction of linguists and programmers in a team
Computational Linguist at ABBYY
Jan 2017 - Sep 2017 | Moscow, Russia
NER - Unit Testing - Ontologies - Knowledge Graphs
- Developed various solutions for Fact Extraction using ABBYY tools
- Implemented unit testing for the Fact Extraction system
Computational Linguistics Intern at ABBYY Labs
Jan 2016 - Jun 2016 | Moscow, Russia
Syntax - Tokenisation & Splitting - Python - Perl - regexp
- Developed the advanced tokenizer for Russian corpora in the Geekrya project
🎓 Education
MA Computational Linguistics | 2017 – 2019
Erasmus Mundus Joint Degree with Erasmus Mundus Scholarship Award:
- Charles University - CUNI (Prague, Czech Republic)
- University of Basque Country - UPV/EHU (San Sebastian, Spain)
BA Fundamental and Applied Linguistics | 2013 – 2017
📚 Projects
Work Projects
- TrustYou Semantic Analysis: Developed a system that performs multilingual Aspect-Based Sentiment Analysis for more than 20 languages using Transformer architecture.
- TrustYou ResponseAI: Developed an automated review response system using LLMs and RAG.
- TrustYou SummaryAI: Developed a review summarisation and key insights extraction system using LLMs and optimized it for a large number of reviews.
- TrustYou Impact Score: Developed an ML system for detecting impactful factors for hospitality businesses.
Open-Source Projects
- HuggingFace Robust Speech Challenge: Developed a speech recognition model for Russian and open-sourced it on the HuggingFace hub. Took part in Feb 2022
- NL-Augmenter: Contributed with a sentiment filter to the NL-Augmenter project that helps with augmentation for sentiment analysis tasks. Took part in Sep 2021
Hackathons
- Junction 2019: The project aimed at encouraging sustainability for retail. Done in collaboration with K Group
- Junction 2018: The project aimed at preventing the SAD condition due to lack of vitamin D for people living in northern countries
University Projects
- Pronunciation Generation for ASR: Developed a pronunciation generation method for ASR based on AWEs. MA thesis in 2019
- Unsupervised Machine Translation: Investigated Cross-Lingual Word Embeddings for Unsupervised Neural Machine Translation for a rus-eng pair. Course project in 2018
- Russian Sketches: Developed the collocation extraction method on the basis of syntactical structure for Russian. BA thesis in 2017
- Amharic Corpus: Developed the Amharic corpus with Part-of-Speech Tagging using a Machine Learning
approach. Presented at the “ConCort” conference on Digital Humanities in 2016
- Tokenizer and Splitter for Russian Web Texts: Developed the advanced tokenizer and splitter for Geekrya corpora. Developed in 2016
- Database of Comparative Constructions: Developed the database of constructions ‘Verb like Noun’ and studied some semantic patterns using this database within a research group. Developed in 2016
- Automatic Authorship Attribution: Investigated different approaches of authorship determination and their statistical evaluation. Presented at the “Digital Humanities” conference in Tartu in 2015
💻 Skills
Technical Skills
- Programming & Development
- Python - Jupyter Notebook - Git - Docker - bash
- Machine Learning & Deep Learning
- RNN - CNN - PyTorch - TensorFlow - Scikit-learn - XGBoost - ONNX
- Natural Language Processing
- BERT - GPT - Word2Vec - FastText - GloVe - TF-IDF - SpaCy - NLTK - Hugging Face Transformers - StanfordNLP - SparkNLP - NLPAug
- Large Language Models & Fine-Tuning
- OpenAI API - Hugging Face Transformers - LangChain - LoRA - PEFT - DeepSpeed
- Data Processing, Feature Engineering & Data Analysis
- Pandas - NumPy - Matplotlib - PySpark
- Databases & Information Retrieval
- PostgreSQL - MySQL - MongoDB - FAISS - Weaviate - ChromaDB - Elasticsearch
- MLOps, Cloud Computing & CI/CD
- AWS - Azure AI - MLflow - Jenkins - Grafana
NLP Skills
In different times, I worked with:
- Text Generation
- Summarisation
- Sentiment Analysis
- Statistical and Neural Machine Translation
- Automated Speech Recognition
- Part-of-Speech Tagging and Parsing
- Word Sense Disambiguation
- Coreference Resolution
- Text Classification and Clusterization
- Information Retrieval
- Named Entity Recognition
- Fact Extraction
using GenAI, transformer-based, statistical and rule-based approaches.
Soft Skills
- Communication & Collaboration
- Technical Writing
- Presentation Skills
- Team Work
- Mentoring
- Leadership & Task Management
- Problem Solving
- Critical Thinking
- Analytical Skills
- Innovation
- Project Planning
- Decision Making
- Accountability
- Research & Development
- Experimentation
- Continuous Learning
- Hypothesis Testing
- Evaluation
Professional Activities
Communication Skills
- Russian (native)
- English (C1)
- German (B2)
- French (A1)
- Spanish (A1)
Other Interests
Language theory - Travelling - Neuroscience - Drawing - Roller and Ice Skating - Yoga - Tennis and Badminton - Writing