Senior Machine Learning Engineer, Time Series Analysis

Role Description:

We're seeking an experienced ML Engineer specializing in time-series modeling. You have extensive expertise throughout the ML lifecycle, from problem definition and exploratory analysis to developing and deploying time-series models into production. You adeptly balance sophisticated modeling techniques with solid engineering practices, consistently integrating robust ML solutions into production environments. You thrive on complex temporal datasets and behavioral insights, driven by creating impactful solutions from concept to user deployment.

Responsibilities:

• Design, develop, and deploy ML models tailored for time-series analysis (e.g., photoplethysmography, MAMBA, dilated 1D CNNs, sparse attention transformers).
• Determine optimal modeling techniques given data, annotation constraints, timelines, and budgets.
• Maintain high-performance production-grade ML services for critical user workflows.
• Monitor and continuously improve model performance using practical real-world metrics.
• Conduct thorough exploratory data analysis to refine feature engineering and model design.
• Work collaboratively with infrastructure teams to optimize data pipelines and ML tooling.
• Clearly translate business needs into structured ML projects and actionable technical plans.
• Stay informed on current time-series research and emerging methods, adapting them effectively.

Requirements

Qualifications:

• 3+ years of applied ML experience, including hands-on deployment of time-series models in production.
• Specialized expertise in time-series modeling, particularly in signal processing or behavioral data.
• Strong proficiency in statistical modeling and extracting signals from noisy temporal data.
• Expert knowledge of Python and at least one major deep learning framework (PyTorch, TensorFlow, JAX).
• Proven ability to transform academic research into practical, production-ready ML solutions.
• Familiarity with MLOps tools, large-scale data systems, and best practices in model management.
• Excellent communication skills, adept at bridging technical concepts to business impacts.

Extra Points:

• Advanced signal processing techniques and experience.
• Experience managing production-grade time-series model deployments.
• Exposure to probabilistic modeling or Bayesian techniques.
• Familiarity with healthcare or other regulated industries, including compliance and validation standards.
• Complementary skills in anomaly detection, forecasting models, IoT systems, or sensor fusion.