As an NLP engineer, I am passionate about using natural language processing technologies to drive impactful results. With a strong background in machine learning and deep understanding of linguistic patterns, I specialize in building models and algorithms that enable computers to parse and analyze human languages.My expertise lies in designing and implementing NLP systems for various tasks, such as sentiment analysis, named entity recognition, text classification, machine translation, text generation. I have experience in preprocessing and cleaning large text datasets, as well as selecting and fine-tuning models for commercial texts generation, topic modeling for user comments and named entity recognition in banking legal texts.I am skilled in Python and have experience with ML and NLP libraries such as NLTK, SpaCy, PyTorch and TensorFlow. Collaboration is a key aspect of my work, and I enjoy working with cross-functional teams to gather requirements, analyze data, and develop solutions.With a strong focus on staying up-to-date with the latest advancements in natural language processing, I am constantly exploring new techniques and methodologies to improve the accuracy and efficiency of NLP systems. I am always seeking innovative approaches to tackle challenges and deliver high-quality results.
-
Nlp EngineerMts Group Mar 2022 - May 2023Moscow, Moscow City, Russia• I developed a model based on RuGPT language model specifically designed for generating advertising texts.• I played a key role in creating an automatic moderation system for advertising texts within the MTS-Marketolog service. -
Visiting LecturerHigher School Of Economics Jan 2023 - Mar 2023Moscow, Moscow City, Russia -
Nlp EngineerSberbank Dec 2017 - Mar 2022Moscow• I supervised the annotation of the bank legal texts for the task of entiuty extraction. I developed guidelines for legal texts annotations. I conducted 3 training sessions for the 25 annotators . As a result, the Cohen Kappa coefficient between annotators increased from 0.3 to 0.7.• I developed a real-time word cloud generation from speech program. The code was used to generate a word cloud in both Russian and English languages in real time during a panel discussion between the presidents of Kazakhstan and Russia at the AI Journey-2020 conference• I used HDBSCAN to topic cluster employee comments about Sputnik V vaccinations• As part of a QA system aimed at assisting Sberbank lawyers in finding previous similar cases more efficiently, I applied LDA and BigARTM machine learning models for topic modeling of judicial texts. These models enabled the system to identify and categorize topics within the texts, allowing lawyers to quickly locate relevant cases based on similarity and relevance. -
InternTampere University Of Applied Sciences Sep 2017 - Oct 2017Tampere, Pirkanmaa, FinlandVisiting intern in international project “Text corpora in training linguistic and translators”• Developed tool for aligning parallel texts in Russian and Finish languages, which helped reduce time consumption for the tasks of this type.
Ivan Smirnov Education Details
-
Applied Linguistics -
Computational And Applied Linguistics -
Gymnasium Protvino
Frequently Asked Questions about Ivan Smirnov
What is Ivan Smirnov's role at the current company?
Ivan Smirnov's current role is ML Engineer (NLP).
What schools did Ivan Smirnov attend?
Ivan Smirnov attended Высшая Школа Экономики, Московский Педагогический Государственный Университет, Высшая Школа Экономики, Gymnasium Protvino.
Not the Ivan Smirnov you were looking for?
Free Chrome Extension
Find emails, phones & company data instantly
Download 750 million emails and 100 million phone numbers
Access emails and phone numbers of over 750 million business users. Instantly download verified profiles using 20+ filters, including location, job title, company, function, and industry.
Start your free trial