# Sergei Tsereshko

Sergei Tsereshko is a remote worker on Himalayas, Senior Data Scientist at UnaFinancial, based in Serbia.

Source: https://himalayas.app/@serg_tser

```text
Data Scientist with 4+ years building ML systems that earn their place in production - by improving real-world decisions, not just offline metrics.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Serbia |
| Authorized to work in | Serbia |
| Salary expectations | 60k-110k EUR |
| Job categories | Data Scientist, Machine Learning Engineer, Machine Learning Developer, Machine Learning Expert, Data Scientist, Data Engineer, Risk Analyst, Search Data Scientist, AI Data Scientist, Data Science Expert, ML Data Scientist, Research Data Scientist |
| Skills | Python, SQL, Machine Learning, AB Tests, PySpark, Airflow, Docker, Gradient Boosting, Git, Power BI, Pandas, NumPy, Scipy, CatBoost, scikit learn, XGBoost, LightGBM, Optuna, ETL, MLFlow, PostgreSQL, MySQL, Hadoop, Matplotlib, SeaBorn, Plotly, Probability, Mathematical Statistics, Data Structures, Linear Algebra, Mathematical Modeling, Telegram |
| Website | https://t.me/Serg_Tser |
| LinkedIn | https://https://www.linkedin.com/in/sergey-tser/ |

## What I'm looking for

```text
Looking for a fully Data Scientist role in product, technology or fintech company. I have 4+ years of experience building and deploying credit scoring and decisioning solutions end to end, including feature generation, A/B testing, production monitoring and portfolio risk analytics. I’m based in Serbia (CET/CEST) and open to full-time roles and long-term contracts.
```

## About

```text
I’m a Data Scientist who builds ML systems that help businesses make better decisions under uncertainty. For more than four years, I’ve worked in consumer lending, where model quality only matters if it leads to the right balance of growth, risk, speed, and cost.

The problems I enjoy rarely begin with an algorithm or end with a model. They start with defining the right objective and understanding the constraints, and they continue long after deployment. I like owning that whole path, especially the trade-offs that appear when a model becomes part of a real decision process.

In practice, I’ve seen a better scoring model add 7–8 Gini points, a carefully designed decision rule raise approval by 4 percentage points without adding risk, and a well-structured experiment turn a scoring change into a 1.5% profit lift. I’m equally interested in the quieter wins around the model: faster decisions, reliable monitoring, and smarter use of external data.

Most of this work happens in Python and SQL, with PySpark on large-scale data and Airflow in production. Credit risk is the domain I know best; the underlying problems—predictive modeling, experimentation, monitoring, and decision optimization—translate far beyond lending.

I’m open to Data Scientist opportunities where ML is connected to a real decision, the outcome is measurable, and I can stay involved from problem framing through production.
```

## Experience

### Senior Data Scientist (current)

UnaFinancial. Jun 2024 - Present

```text
Built production credit-scoring models from credit-history and mobile-app data, improving Gini by 8 pp and cutting delinquency by 2–4 pp while maintaining approval rates. Generated and screened 8,000+ features. Developed risk rules that increased approval by 4 pp without higher delinquency. Automated monitoring with Airflow and built an AI agent for daily risk-rule anomaly detection.
```

Skills: Big-Data, fastAPI, Credit-Risk, Data-Analysis, Mathematical-Modeling, Mathematics, Math-education, Statistics, Mathematical-Statistics, AB-Tests, Model-Validation, Monitoring, Model-Monitoring, Probability, Linear-Algebra, Python, SQL, PySpark, Power-BI, Airflow, JupyterLab, Jupyter, Git, Gitlab, CatBoost, XGBoost, Gradient-Boosting, Optuna, Matplotlib, SeaBorn, scikit-learn, Scipy, PostgreSQL, MySQL, Pandas, NumPy, Plotly, Docker, Credit-Scoring, Feature-Engineering, JupyterHub, Risk-Analytics, Portfolio-Analytics

### Data Scientist

ID Finance. May 2022 - Jun 2024

```text
Owned the full lifecycle of a credit-scoring model that reached Gini above 0.60, outperforming the baseline by 7 pp with CatBoost. Ran and analyzed A/B tests of score cutoffs, selecting a configuration that lifted profit by 1.5% at an unchanged default rate. Developed automated credit decisioning that cut loan processing time by 13%.
```

Skills: Jupyter, Jupyter-Notebooks, Pandas, NumPy, PostgreSQL, Greenplum, S3, fastAPI, Gradient-Boosting, CatBoost, XGBoost, LightGBM, Docker, ETL, Git, scikit-learn, Big-Data, AB-Tests, Credit-Risk, Credit-Scoring, SeaBorn, Probability, Mathematics, Math-education, Mathematical-Modeling, Statistics, Data-Science, Mathematical-Statistics, Linear-Algebra, Python, SQL, Data-Analysis

## Education

### Novosibirsk State University

Bachelor or mathematics, Applied Mathematics and Computer Science. 2021 - 2025. Grade: 4.8

Activities and societies: Participated in university mathematics olympiads and university sports competitions, achieving podium finishes in several events.

```text
Graduated with honors in Applied Mathematics and Computer Science (GPA: 4.8/5.0), with a focus on mathematical modeling and numerical methods. For my bachelor's thesis, I developed and validated a Python model of landslide-generated surface waves and coastal run-up using the Large Particle Method.
```

## Tech stack

- GitLab
- Jupyter
- NumPy
- Pandas
- PySpark
- MySQL
- PostgreSQL
- Hadoop
- Greenplum Database
- Telegram
- Python
- PowerShell
- MLflow
- scikit-learn
- Git
- Docker
- Airflow
- Microsoft Power BI
- SQL
- XGBoost
- SciPy
- LightGBM
- CatBoost
- Optuna
- Seaborn

To contact Sergei, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Andrey Gort](https://himalayas.app/@andreygort): Chief Data Officer, Digital Finance International
- [Igor Poletaev](https://himalayas.app/@igorpoletaev): Data Analyst / BI Developer, Sberbank
- [Vladislav Kiryachek](https://himalayas.app/@vladislavkiriachek): ML Engineer | Data Scientist, SIBUR Digital LLC
- [Aleksandr Shchegolev](https://himalayas.app/@aleksandrshchegolev): Artificial Intelligence Engineer, ВБ digital
- [George Maltsev](https://himalayas.app/@georgemaltsev): Senior Machine Learning Engineer, UBS
- [Ognjen User](https://himalayas.app/@ognjenuser): Data Science Intern, Schneider Electric
- [Tijana Bajić](https://himalayas.app/@tijanabaji): Junior Data Scientist, Ominimo Insurance
- [Bata Khasykov](https://himalayas.app/@batakhasykov): System Administrator, Social Fund of Russia
- [Игорь Климов](https://himalayas.app/@0008996): ML Engineer, Yandex
- [Sara Trnjakov](https://himalayas.app/@saratrnjakov): Data Analyst, Introba
