
Innopolis University BS22 | NLP & RecSys | Yandex
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Yandex
Data Scientist
June 29, 2026 – Present
fusion_chain_experiment
October 11, 2025 – October 14, 2025
fusion_chain_experiment — GitHub repository
View ProjectS25-Data-Mining-Project
May 10, 2025 – May 11, 2025
S25-Data-Mining-Project — GitHub repository
View ProjectToxicTune-DPO-Based-LLM-Toxification
April 10, 2025 – April 10, 2025
This repository provides a Kaggle competition solution that adapts a movie review language model into a toxic responder using Direct Preference Optimization (DPO). It demonstrates how to prepare toxic vs. benign responses, apply DPO training, and generate a submission file.
View Projectbigdata_course_project
April 5, 2025 – May 7, 2025
🚀 Team14 bigdata course project: Kaggle → Hive → Spark-SQL → ML → Superset
View ProjectReal-time_Number_Plate_Recognition
October 6, 2024 – November 25, 2024
Building, deploying, and comparing a real-time licence plate recognition system with YOLOv5, YOLOv11, and OCRs
View ProjectSentiment_Analysis_for_Financial_News
September 19, 2024 – December 5, 2024
Building, experimenting, and deploying a machine learning-based solution for sentiment analysis on financial news articles
View ProjectMRI-Diagnosis-API
September 17, 2024 – September 19, 2024
Deployment of ML model for brain tumor detection in an API and a web application that interacts with this API. The deployment utilizes Docker containers, FastAPI for the model API, and Streamlit for the web application.
View ProjectReProcess
June 6, 2024 – October 21, 2024
Tool designed for managing dependencies within code repositories
View ProjectCultural Fit Analysis
The candidate's personal projects demonstrate a strong interest and initiative in exploring various data science applications, from LLM toxification to medical imaging and financial news sentiment. This diversity suggests a curious and adaptable individual. The 'bigdata_course_project' also indicates experience in team-based project work. The current role at Yandex as a Data Scientist aligns well with the target role, suggesting a good cultural fit for a data-driven environment. However, the lack of detailed descriptions for some projects ('fusion_chain_experiment', 'coco-eval', 'S25-Data-Mining-Project') limits the depth of this assessment.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a proactive approach to learning and applying diverse data science techniques. The focus on deployment (Docker, FastAPI, Streamlit) suggests an understanding of bringing models to production, which is valuable for operational fit. However, without psychometric or English test scores, a comprehensive assessment of soft skills, logical reasoning, work attitude, stress handling, and team collaboration is not possible.