Data Scientist

Data Scientist / ML Engineer (Bioinformatics & Physiological Data)

Type: Contract (project-based, with possibility of extension)

Location: Remote / Flexible in Minsk, Belarus

⸻

Role Overview

We are seeking a Data Scientist / ML Engineer with strong experience in bioinformatics, time-series analysis, and applied machine learning to build data-driven systems for physiological and biomarker data. The role centers on Google Cloud Platform (GCP) as the primary environment, while also requiring integration with external physiological simulation engines.

A distinctive aspect of this role is the integration of female-specific physiological and hormonal data (e.g., menstrual cycle phases, hormone-linked biomarker shifts). Candidates with experience, interest, or research exposure in women's physiology will be especially well-positioned to contribute.

⸻

Key Responsibilities

• Develop and maintain ETL pipelines from biosensors, lab tests, and APIs into BigQuery.

• Engineer features from physiometric time-series data (HR, HRV, sleep, load, thermal strain) and biomarker datasets.

• Train, validate, and deploy machine learning models in Vertex AI (AutoML and custom pipelines).

• Integrate with external physiological modeling engines (e.g., Pulse) to expand predictive capacity.

• Deploy models as APIs/microservices (FastAPI, Flask, Cloud Run) and manage their lifecycle.

• Build dashboards and decision-support layers in Looker Studio connected to BigQuery.

• Apply bioinformatics methods to structure and interpret biomarker data, including sex-specific and hormonal variables.

• Collaborate with domain experts to ensure models deliver actionable, physiologically valid outputs.

⸻

Skills & Qualifications (Required)

• Python expertise for data science and backend development.

• Strong proficiency in Google Cloud Platform tools: BigQuery, Vertex AI, Cloud Functions/Run, GCS, Looker Studio.

• Hands-on experience with time-series analysis and feature engineering.

• Proven ability with machine learning frameworks: Scikit-learn, TensorFlow or PyTorch, gradient-boosted trees (XGBoost, LightGBM, CatBoost).

• Familiarity with bioinformatics or biomedical data pipelines, including biomarkers.

• Experience deploying APIs/microservices with Flask or FastAPI.

• Proficiency with MLOps practices (MLflow, experiment tracking, Docker, version control).

• Comfort working with female physiology datasets, including hormonal or menstrual cycle data.

• Professional working proficiency in English (spoken and written).

⸻

Ideal Candidate Profile

• Degree in Data Science, Bioinformatics, Computational Biology, or Computer Science (advanced degree welcome).

• Track record of building end-to-end ML pipelines from data ingestion to deployment.

• Interest in applying bioinformatics and machine learning to human performance, recovery, and resilience domains.

• Strong problem-solving mindset, comfortable with project-based contract work and iterative deliverables.

⸻

What We Offer

• Opportunity to work on cutting-edge applications of bioinformatics, ML, and physiology.

• Direct impact on projects at the intersection of data science, women's physiology, and high-performance systems.

• Flexible, research-driven working environment with clear deliverables.

• Contract engagement with the potential for long-term collaboration.