Senior Machine Learning Architect/Scientist - Telemetry and Log Analytics

Overview

This role focuses on pioneering advanced data science techniques to enable businesses to derive critical insights from massive telemetry and log datasets. You will lead cutting-edge work combining new statistical methods, models, and analytic architectures, collaborating with top academics, industry experts, and engineers to transform petabyte-scale data into actionable intelligence.

Key Responsibilities

• Lead the end-to-end design and execution of modelling strategies and analytic architectures for telemetry and log data, from conceptualization to deployment, ensuring solutions meet scalability, reliability, and observability standards.
• Develop sophisticated models for time-series and event logs, including techniques such as anomaly detection, forecasting, change-point identification, pattern discovery, correlation analysis, root-cause analysis, and natural language processing for unstructured logs.
• Define architectural frameworks and technical requirements for both batch and real-time streaming analytical pipelines, such as data contracts, schemas, feature stores, and model serving mechanisms, in close collaboration with data and platform engineering teams.
• Continuously monitor emerging advancements in machine learning, time-series analysis, and observability domains and integrate innovative technologies into team projects.
• Serve as a thought leader by inspiring innovation, advocating best practices, mentoring colleagues, and contributing to intellectual property, research papers, and white papers in the field.

Essential Qualifications and Experience

• Over 10 years of professional experience in applied sciences or complex software systems, especially involving machine learning applied to telemetry, log, or observability data with demonstrable production impact.
• Expertise in various modelling approaches such as anomaly detection, forecasting, change-point detection, pattern mining, correlation analysis, root-cause analysis, and NLP methodologies including template mining, embeddings, topic modeling, and classification.
• Advanced skills in Python programming, SQL, and designing ETL pipelines, preferably with Airflow, with strong understanding of time-series feature engineering, statistical evaluation, and experimental design.
• Knowledge of observability toolsets like ELK/Elastic, Splunk, Azure Monitor, Datadog, Grafana/Loki, and OpenTelemetry, and practical experience in model governance and MLOps practices.

Desirable Attributes

• Advanced degree (PhD or Master's) in Technology, Computer Science, Machine Learning, or a related quantitative discipline.
• In-depth familiarity with sophisticated telemetry/log-related modeling techniques, including state-space models, ARIMA/ARIMAX/Prophet, gradient boosting trees, anomaly and seasonality decomposition, causal inference, time-series feature extraction, sequence mining, clustering, and deep learning for sequential data.
• Ability to define and implement SLO/SLI-driven ML models for observability platforms and work closely with Site Reliability Engineering, platform, and support teams.
• Track record of contributions such as research publications, patents, or open-source projects showcasing thought leadership in ML, analytics, observability, or reliability engineering.

Additional Information

Dell Technologies cultivates an inclusive workplace that nurtures innovation by embracing diversity and ensuring an environment free from discrimination and harassment.

The role is located onsite in Cork, Ireland, and offers the chance to join a dynamic team committed to advancing machine learning methodologies to solve complex real-world problems.