Sr Data Scientist

Job Description Summary

The Sr Staff Data Scientist is a senior technical leader who shapes and delivers high-impact Data Science and Machine Learning solutions for industrial operations across Oil & Gas, Fossil Power, and Renewable Power. You will lead small teams/programs, set best practices for the end-to-end ML lifecycle, and partner with business and engineering leaders to translate operational challenges into predictive and prescriptive solutions that drive measurable outcomes (reliability, availability, efficiency, emissions, cost).

This role requires deep experience with time-series forecasting, anomaly detection, and predictive maintenance on large industrial datasets, with Generative AI as a value-adding plus. Candidates must bring a minimum of 8 years’ experience in operations, maintenance or monitoring of at least one of the above industry domains.

Hybrid role: in office

• Collaborate with business/domain leaders to identify, prioritize, and scope high-value ML use cases (e.g., time-series forecasting, anomaly detection, predictive maintenance), define success metrics, and ensure measurable business impact.
• Lead and oversee the end-to-end DS/ML lifecycle: data acquisition, cleaning, feature engineering, and exploratory analysis for industrial datasets (sensor/telemetry, production logs, emissions, maintenance history).
• Develop, validate, and tune models across regression, classification, time-series (ARIMA/Prophet/LSTM/GRU/state-space), anomaly detection, and ensembles; apply deep learning when appropriate; ensure robust cross‑validation and reproducibility.
• Deploy models to production on cloud platforms (AWS/Azure/GCP); guide choices for model serving, latency, throughput, and scalability;
  Own and influence the ML systems architecture
  , including model lifecycle management, feature pipelines, CI/CD for ML, observability, drift detection, and retraining strategies; partner with platform teams to define scalable and compliant ML‑Ops patterns.
• Partner with data/platform engineering to operationalize pipelines and integrate models into business applications and workflows; ensure reliability, observability, and SLAs.
• Establish and champion standards, reusable assets, and best practices for data quality, governance, security-by-design, and validation across programs.
• Mentor and coach data scientists/analysts; perform code/model reviews; grow skills and foster a strong data science culture; lead small teams/projects with moderate risk and complexity.
• Translate model outcomes into clear, actionable insights for technical and non‑technical stakeholders; communicate trade‑offs, risks, and assumptions; quantify value realization.
• Collaborate with Reliability Engineering to apply reliability analytics (e.g., Weibull analysis, survival/hazard models, RGA/Crow‑AMSAA), integrate CMMS/EAM/APM and historian/SCADA data, and inform maintenance and spares strategies where applicable.
• Stay current with advancing ML methods (especially industrial IoT analytics, streaming/real‑time) and evaluate/pilot GenAI/LLM‑assisted workflows (e.g., analytics automation, documentation, knowledge retrieval) as an added advantage.
• Contribute to functional data/analytics strategy and roadmaps; influence cross‑functional ways of working; ensure alignment with GE Vernova standards and compliance requirements.

• Bachelor's Degree in Computer Science or “STEM” Majors (Science, Technology, Engineering and Math) with minimum 10 years of experience.
• Master’s/PhD preferred.

• Expert proficiency in Python and SQL; strong in libraries such as Pandas, Num Py, scikit‑learn; experience with Tensor Flow/PyTorch where deep learning is applicable.
• Advanced time‑series and anomaly detection for industrial data; predictive maintenance modeling and feature engineering for sensor/telemetry and maintenance data.
• Cloud ML platforms (e.g., AWS Sage Maker, Azure ML, GCP Vertex AI), CI/CD for ML, model registries, monitoring and drift detection; design for scalable, reliable serving.
• Data management practices at scale: data quality and cleansing strategies, governance…