Intuitive
Job Description
Primary Function of Position
The Sr Data Scientist Product Performance leverages deep expertise in data science, machine learning, statistical modeling and analytics to enhance product telemetry and service technology across Intuitive’s portfolio. The role is responsible for building robust data pipelines, developing advanced ML/AI models, and collaborating with cross‑functional teams to advance proactive and predictive service initiatives. The position also ensures compliance with regulatory standards and continuously drives innovation and data‑driven improvements in product performance and customer experience.
Roles & Responsibilities
Design, deploy, and maintain both supervised and unsupervised machine learning models to support proactive diagnostics, anomaly detection, classification, and time‑series forecasting (e.g., part failure, inventory management).
Leverage LLMs, NLP techniques, and regular expressions to extract, clean, and structure data from semi‑structured text. Fine‑tune domain‑specific LLMs for tasks like entity extraction and complaint record classification, ensuring high‑quality data for analysis.
Apply time‑series models (statistical, ML and sequence models) for survival analysis and predictive modeling of component and system lifecycles.
Develop workflow automation tools that incorporate human‑in‑the‑loop feedback cycles to improve performance and reliability. These tools will effectively blend automation with expert review, resulting in more robust and adaptable solutions.
Expand data ingestion pipelines to integrate diverse sources such as system log data, CRM, customer complaint and field service data to automate and streamline troubleshooting and failure analysis reporting.
Develop and manage dashboards, visualizations, and analytics to communicate key insights and model results to a range of audiences, from technical staff to senior leadership.
Lead cross‑functional investigations and stakeholder feedback loops for continuous model improvement, engaging with Services Product Management, engineering, and clinical teams.
Collaborate with other engineering teams to uphold data governance and accelerate the integration of advanced analytics solutions into products and workflows.
Conduct additional analysis/activities across the product/service lifecycle, as needed, to support product telemetry and service tech evolution and advancement.
#J-18808-Ljbffr
Roles & Responsibilities
Design, deploy, and maintain both supervised and unsupervised machine learning models to support proactive diagnostics, anomaly detection, classification, and time‑series forecasting (e.g., part failure, inventory management).
Leverage LLMs, NLP techniques, and regular expressions to extract, clean, and structure data from semi‑structured text. Fine‑tune domain‑specific LLMs for tasks like entity extraction and complaint record classification, ensuring high‑quality data for analysis.
Apply time‑series models (statistical, ML and sequence models) for survival analysis and predictive modeling of component and system lifecycles.
Develop workflow automation tools that incorporate human‑in‑the‑loop feedback cycles to improve performance and reliability. These tools will effectively blend automation with expert review, resulting in more robust and adaptable solutions.
Expand data ingestion pipelines to integrate diverse sources such as system log data, CRM, customer complaint and field service data to automate and streamline troubleshooting and failure analysis reporting.
Develop and manage dashboards, visualizations, and analytics to communicate key insights and model results to a range of audiences, from technical staff to senior leadership.
Lead cross‑functional investigations and stakeholder feedback loops for continuous model improvement, engaging with Services Product Management, engineering, and clinical teams.
Collaborate with other engineering teams to uphold data governance and accelerate the integration of advanced analytics solutions into products and workflows.
Conduct additional analysis/activities across the product/service lifecycle, as needed, to support product telemetry and service tech evolution and advancement.
#J-18808-Ljbffr