Sr. Data Scientist

Job Description Summary

• The Sr Data Scientist Engineer delivers end-to-end Data Science and Machine Learning solutions for industrial operations with a focus ontime-series forecasting, anomaly detection, and predictive maintenance
• You will lead assigned workstreams as an individual contributor,translate business goals into technical requirements, and productionize models on cloud platforms in partnership with data/platformengineering
• The emphasis is on rigorous model development, validation, and lifecycle execution to achieve measurable outcomes (reliability,availability, efficiency, emissions, cost)
• Candidates should have a minimum of 4 years?? experience in operations within at least one of Oil &Gas, Fossil Power, or Renewable Power
• Experience with Generative AI (GenAI) is an added advantage
• Reliability analytics exposure (e g ,Weibull analysis, survival/hazard modeling, RGA/Crow-AMSAA, ReliaSoft or open-source equivalents) is preferred

Job Description

Roles and Responsibilities

• Own and lead assigned DS/ML workstreams as an individual contributor: collaborate with stakeholders to frame problems and agree success metrics, then deliver to plan.
• Perform data acquisition, quality assessment/cleansing, feature engineering, and exploratory analysis across industrial datasets (sensor/telemetry, production logs, emissions, maintenance history), ensuring reproducibility.
• Develop, tune, and validate models (regression, classification, time-series such as ARIMA/Prophet/LSTM/GRU/state-space; anomaly detection; ensembles; deep learning where applicable) with robust cross-validation and clear documentation.
• Deploy and operationalize models on cloud ML platforms (AWS/Azure/GCP) under established practices; contribute to serving choices and implement monitoring, drift detection, and retraining per defined policies in collaboration with MLOps and platform teams.
• Build maintainable, production-ready assets for assigned use cases: pipelines, experiment tracking, code quality, and reusable components; adhere to governance, security, and reliability/SLAs.
• Translate model outcomes into actionable insights for technical and non-technical stakeholders; communicate trade-offs, risks, and assumptions; track value against success metrics.
• Provide informal mentorship (code reviews, modeling best practices) to junior team members; contribute templates and documentation to improve ways of working.
• Contribute to pilots/POCs in GenAI/LLM-assisted workflows (analytics automation, documentation, knowledge retrieval) as an added advantage.
• Where applicable, partner with Reliability Engineering to apply reliability-focused models (e.g., Weibull/survival/RGA) and integrate CMMS/EAM/APM and historian/SCADA data to inform maintenance and spares decisions.
• Stay current with advances in industrial ML (e.g., streaming/real-time) and apply incremental improvements to methods and patterns.

Education Qualification

• For roles outside USA: Bachelor''s Degree in Computer Science or ??STEM? Majors (Science, Technology, Engineering and Math) with minimum 5 to 8 years of experience in Data Science/Machine Learning or closely related roles. Master??s preferred.
• For roles in USA: Bachelor''s Degree in Computer Science or ??STEM? Majors (Science, Technology, Engineering and Math) with minimum 8 years of experience. Master??s preferred.

Desired Characteristics

Technical Expertise:

• Proficient in Python and SQL with libraries such as Pandas, NumPy, scikit-learn; experience with TensorFlow/PyTorch where deep learning is applicable.
• Strong applied time-series and anomaly detection for industrial data; hands-on with feature engineering and model validation practices.
• Experience deploying on cloud ML platforms (e.g., AWS SageMaker, Azure ML, GCP Vertex AI); familiarity with MLOps (CI/CD for ML, model registry, monitoring, drift detection, retraining).
• Solid data management practices: ETL fundamentals, data quality assessment/cleansing, and awareness of governance/security controls.
• Familiarity with big data/streaming technologies (e.g., Spark, Kafka) and real-time analytics considerations is a plus.
• Preferred/added advantage: Reliability analytics methods and tools (Weibull, survival/hazard modeling, RGA/Crow-AMSAA; ReliaSoft suite or open-source equivalents such as lifelines/scikit-survival). GenAI/LLM-enablement for analytics acceleration.

Domain Knowledge:

• Minimum 4 years?? experience in operations within at least one of: Oil & Gas, Fossil Power, Renewable Power; ability to connect operational realities (failure modes, maintenance strategies, process constraints) to features, validation criteria, and deployment constraints.
• Demonstrated business understanding: map analytics to operational KPIs (availability, MTBF/MTTR, throughput, energy yield, emissions, cost) and articulate value/ROI trade-offs.

Leadership:

• Operates with some autonomy within standard practices; primarily an individual contributor with strong interpersonal skills; provides informal guidance to new team members.
• Structured problem solving with the ability to propose options beyond set parameters (with guidance); collaborates across functions to execute effectively.
• Consulting mindset: translates requirements and trade-offs for stakeholders; provides researched recommendations with documented assumptions.
• Acts as a change agent at team level: adopts new methods/tools and drives continuous improvement in ways of working.

Personal Attributes:

• Curiosity and creativity: explores new approaches and connects ideas from adjacent domains to improve outcomes.
• Comfort in ambiguity: delivers with assumptions where needed and course-corrects based on feedback; communicates status and limitations clearly.
• Strong communication and collaboration skills: tailors messages to varied audiences and contributes to a positive, high-performance team culture.