# Mikhail Zemskov

Mikhail Zemskov is a remote worker on Himalayas, Machine Learning Engineer / Data Engineer at Autonomous Driving Technology Company, based in Russian Federation.

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

```text
Machine Learning Engineer at an autonomous driving technology company who improved a deployed 3D detector’s mAP by 2%.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | Russian Federation |
| Authorized to work in | Russian Federation |
| Salary expectations | 40k+ USD |
| Job categories | Machine Learning Engineer, Data Engineer |
| Skills | Machine Learning, Computer Vision, 3D Detection, Semantic Search, Deep Learning, MLOps, ETL, Data Vault, Data Quality, Model Training, Model Validation, Model Deployment, OCR, Python, PyTorch |
| Portfolio | https://github.com/Mishardina/sam-image-labeler |
| GitHub | https://github.com/Mishardina |

## What I'm looking for

```text
I'm open to part-time and contract roles.
```

## About

```text
At an autonomous driving technology company, I automate terabyte-scale training-data workflows for 3D object detection, from ingestion and quality checks to model integration. I improved a real-time detector’s mAP by 2% relative to baseline, and the model was deployed on the target platform.

At Nibelung.AI, I developed and deployed semantic-search models for e-commerce, including embedding models that improved NDCG by an average of 45% relative to baseline across three clients. I also developed a multi-client model for ranking search results.

In data engineering roles at VTB, Beeline, Sberbank / SberDevices, and Magnit, I developed or maintained ETL, streaming, and batch pipelines, data marts, and data quality checks. My work included processing terabyte-scale datasets and contributing to enterprise data infrastructure.

Through freelance computer vision projects, I built license plate recognition for challenging imaging conditions, OCR for Japanese documents, the Strelok-CV automated judging system, and video emotion recognition. I also contributed to an EEG-based system for early detection of depressive disorders at Brainify.AI.
```

## Experience

### Machine Learning Engineer / Data Engineer (current)

Autonomous Driving Technology Company. Oct 2025 - Present

```text
Automated ingestion and preparation of terabyte-scale training data for 3D object detection, developed and maintained processing pipelines and quality checks. Investigated 3D detection approaches, integrated models into a real-time system, and improved the real-time detector's mAP by 2% relative to baseline.
```

Skills: Python, PyTorch, OpenCV, C++, Dagster, LakeFS, S3, Clickhouse, ClearML, ROS

### Machine Learning Engineer

Nibelung.AI. Oct 2024 - Jun 2026

```text
Developed and deployed semantic-search models for e-commerce, from data preparation and synthetic example generation to training and validation pipelines. Built embedding models that delivered an average 45% relative improvement in NDCG over baseline across 3 clients.
```

Skills: Python, PyTorch, Transformers, OpenSearch, Clickhouse, OpenAI-API, TorchServe, CatBoost

### Data Engineer

VTB. Oct 2024 - Oct 2025

```text
Developed and maintained 10+ ETL pipelines and Data Vault data marts for financial modeling, processing terabyte-scale datasets. Contributed to enterprise data warehouse architecture, prepared code and artifacts for releases, and supported pipelines and data marts in production.
```

Skills: Apache-Spark, Iceberg, Python, Hive, Hadoop, Airflow

### Freelance ML / Computer Vision Projects

Self Employed. Aug 2021 - Mar 2025

```text
Built license plate recognition for challenging imaging conditions and OCR for Japanese documents; developed the Strelok-CV automated judging system and video emotion recognition.
```

Skills: Python, C++, PyTorch, TensorFlow, OpenCV, YOLO, OCR, Onnx, TensorRT

### Data Engineer

Beeline. Feb 2024 - Oct 2024

```text
Independently designed and implemented ETL pipelines for regulatory reporting on terabyte-scale data, covering source analysis, Spark ingestion from PostgreSQL into HDFS, and output validation. Prepared data extracts and Qlik Sense reports; checked and analyzed the resulting datasets.
```

Skills: Hadoop, Spark, PostgreSQL, Python, Airflow, GitLab-CI-CD, Kafka, Apache-Flink, Qlik-Sense

### Data Engineer

Sberbank / SberDevices. Oct 2023 - Feb 2024

```text
Developed and maintained 10+ streaming and batch pipelines for telemetry, user activity, and structured data at terabyte scale. Built data delivery and quality-checking procedures and contributed to enterprise data management infrastructure.
```

Skills: Spark, PostgreSQL, Clickhouse, Kubernetes, GitLab-CI-CD, Huawei-Cloud

### Data Engineer

Magnit. Jan 2023 - Oct 2023

```text
Automated ETL workflows for ML training data and developed a Data Vault warehouse; implemented testing and data quality checks, standardized development workflows, and contributed to MLOps practices.
```

Skills: Python, Airflow, Spark, Greenplum, IBM-DB2, Flask, Docker, Kubernetes, Yandex-Cloud

### Junior Cloud Engineer

[IBM](https://himalayas.app/companies/ibm-com). Feb 2022 - Jul 2022

```text
Built MVP components for cloud applications on an open-source stack and performed integration testing using OpenStack, Docker, Podman, Java, and Open Liberty.
```

Skills: OpenStack, Docker, Podman, Java, Open-Liberty

### Junior Data Scientist

Brainify.AI. Mar 2021 - Mar 2022

```text
Contributed to an EEG-based system for early detection of depressive disorders: analyzed data and research literature, implemented models, and built preprocessing for data from multiple sources using Python and PyTorch.
```

Skills: Python, PyTorch

## Education

### Moscow Aviation Institute (MAI)

Specialist Degree, Integrated Aircraft Systems. 2018 - 2024

```text
Specialist Degree in Integrated Aircraft Systems from Moscow Aviation Institute (MAI) from 2018 to 2024.
```

## Tech stack

- Apache Spark
- Kubernetes
- dbt
- MySQL
- PostgreSQL
- MongoDB
- Hadoop
- IBM DB2
- OpenCV
- Python
- Java
- C++
- TensorFlow
- PyTorch
- scikit-learn
- Kafka
- Flask
- Transformers
- OpenStack
- Linux
- OpenSearch
- Docker
- Airflow
- XGBoost
- LightGBM
- CatBoost
- Clickhouse
- Dagster
- Podman
- OpenAI API
- LakeFS
- Trino
- ClearML
- Optuna
- Huawei Cloud

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

## People also viewed

- [Maxim Kryzhanovskiy](https://himalayas.app/@maximkryzhanovskiy): Machine Learning Engineer, T Bank
- [Karen Yepremyan](https://himalayas.app/@karenyepremyan): AI Team Lead, MWS (Mobile Web Services)
- [Alex283h Luzgin](https://himalayas.app/@Aleksandr): Machine Learning Research Engineer, Paylin
- [Aleksandr Tomaev](https://himalayas.app/@aleksandrtomaev): ML Engineer (DS Projects), DS Projects
- [Konstantin Sviblov](https://himalayas.app/@konstantinsviblov): ML Engineer, Wildberries
- [Глеб Бобровских](https://himalayas.app/@bobrg): Research Engineer, Skolkovo Institute
- [Денис Колосков](https://himalayas.app/@0006100): ML Assessor, Yandex Crowd
- [Kerim Gorn](https://himalayas.app/@kerimgorn): AI Engineer, T Bank
- [Philip Konokhov](https://himalayas.app/@philipkonokhov): Machine Learning Engineer, Self Driving, Yandex
- [Михаил Яснов](https://himalayas.app/@0008600): AI Technical Expert, DSSL
