About the Role
We are looking for an experienced Senior Machine Learning Engineer to join our R&D and engineering team and contribute to the research and development of advanced machine-learning solutions in healthcare and medical technology.
The successful candidate will focus on researching, designing, implementing, and evaluating machine-learning algorithms, particularly for multivariate time-series analysis, predictive modeling, forecasting, and anomaly detection.
The role involves working with scientific research, publicly available datasets, and diverse data sources to develop and evaluate practical machine-learning approaches.
The candidate will also collaborate closely with backend and data engineering specialists to define data structures, acquisition requirements, quality criteria, and processing specifications necessary for effective machine-learning development.
We are looking for someone with genuine hands-on machine-learning expertise, scientific thinking, and the ability to translate research into reproducible algorithmic implementations.
Key Responsibilities
Machine Learning Research & Development
Research, design, and implement machine-learning algorithms.
Develop and evaluate predictive models using classical machine learning and deep learning techniques.
Investigate appropriate architectures for sequential and multivariate time-series data.
Develop forecasting, classification, pattern-recognition, and anomaly-detection solutions.
Conduct experiments, benchmark algorithms, and document results.
Review scientific publications and translate relevant research into practical implementations.
Time-Series Analysis & Predictive Modeling
Develop methods for multivariate time-series analysis and forecasting.
Investigate temporal dependencies and relationships among variables.
Implement feature-engineering and feature-extraction techniques.
Develop supervised, unsupervised, and semi-supervised learning approaches.
Investigate methods for handling missing, noisy, irregular, and heterogeneous data.
Evaluate model robustness, generalizability, and predictive performance.
Dataset Research & Experimental Development
Identify and evaluate publicly available datasets relevant to healthcare, biomedical engineering, and time-series analytics.
Assess dataset quality, structure, completeness, and suitability for machine-learning applications.
Investigate dataset limitations, licensing, and permitted research use.
Develop experimental models using appropriate datasets.
Reproduce and benchmark selected research methodologies.
Document experimental findings, assumptions, and limitations.
Data Requirements & Engineering Collaboration
Collaborate with backend and data engineers to define machine-learning data requirements.
Identify required features, input variables, labels, and target variables.
Specify relevant temporal resolution, sampling, and timestamping requirements.
Define data-quality and preprocessing requirements.
Identify missing data elements and additional data requirements.
Contribute to defining data structures suitable for training, evaluation, and inference.
Review dataset suitability and provide technical feedback to data engineering teams.
Model Evaluation & Engineering
Establish appropriate training, validation, and testing methodologies.
Select relevant evaluation metrics for different modeling tasks.
Apply appropriate data-splitting strategies and prevent data leakage.
Evaluate model performance, robustness, and generalizability.
Investigate model calibration, interpretability, and uncertainty where appropriate.
Develop modular and reproducible machine-learning code.
Collaborate with backend engineers on model interfaces and integration requirements.
Document model architecture, limitations, and experimental results.
Required Qualifications
Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Machine Learning, Mathematics, Biomedical Engineering, or a related discipline.
At least 3 years of relevant practical experience in machine-learning development.
Strong programming proficiency in Python.
Practical experience with PyTorch, TensorFlow, or equivalent machine-learning frameworks.
Strong understanding of machine-learning algorithms and statistical learning.
Practical experience with time-series analysis and predictive modeling.
Experience in feature engineering and data preprocessing.
Experience developing and evaluating forecasting, classification, or anomaly-detection models.
Strong understanding of model evaluation, validation, and performance metrics.
Experience working with structured and sequential datasets.
Ability to translate research into practical algorithmic implementations.
Preferred Qualifications
Experience with multivariate time-series forecasting and analysis.
Familiarity with LSTM, GRU, TCN, and Transformer-based architectures.
Experience with statistical forecasting and anomaly-detection techniques.
Experience with NumPy, pandas, SciPy, and scikit-learn.
Familiarity with XGBoost, LightGBM, or similar algorithms.
Experience handling noisy, missing, and imbalanced datasets.
Experience with healthcare analytics, biomedical signal processing, or physiological time-series data.
Familiarity with public research datasets and scientific experimentation.
Experience with MLflow, model versioning, reproducibility, and MLOps.
Familiarity with Docker, APIs, and model-serving technologies.
Personal & Professional Competencies
Strong scientific, analytical, and problem-solving skills.
Ability to independently investigate research questions and evaluate algorithmic approaches.
Practical and evidence-based approach to model development.
Strong technical documentation and communication skills.
Ability to collaborate effectively with software and data engineers.
Ability to translate machine-learning requirements into clear technical specifications.
High degree of responsibility, ownership, and professional integrity.
Interest in applying machine learning to complex healthcare and medical technology challenges.
What We Offer
The opportunity to work on advanced machine-learning applications in healthcare and medical technology.
Involvement in applied AI research and algorithm development.
Collaboration with multidisciplinary software engineering and data science teams.
Opportunities to work on complex time-series and predictive modeling problems.
Professional growth through scientific research and practical machine-learning development.
Position Objective: Research, design, develop, and evaluate machine-learning algorithms for time-series analysis, predictive modeling, and anomaly detection, contributing to the technical foundations for future intelligent healthcare applications.