Sr Data Scientist

Responsibilities:

·        Partner with product and business stakeholders to translate ambiguous asks into clear AI/ML use cases

·        Own product relationships for assigned use cases by managing expectations, surfacing risks early, and aligning stakeholders around tradeoffs and business outcomes

·        Lead exploratory analysis, feature engineering, model selection, experiment design, and statistical validation for time series, forecasting, anomaly detection, and other IoT-oriented use cases

·        Work with IoT and sensor-based data, including irregular intervals, missingness, and event-driven signals

·        Define strong baseline approaches and recommend the simplest effective solution

·        Build and evaluate predictive, optimization, and GenAI-enabled solutions using reproducible workflows in Databricks

·        Help define and deliver data products that are reusable, maintainable, and valuable to downstream users, systems, or business processes

·        Use GitHub and Azure DevOps with strong version control, pull request discipline, documentation, and work tracking practices

·        Contribute to API-oriented solution design by shaping model inputs/outputs, integration expectations, and consumption patterns for downstream applications

·        Mentor junior and mid-level data scientists and contribute reusable templates and team standards

Skills: 

·        6+ years of experience in data science, machine learning, or applied AI with a track record of delivering business-impacting solutions

·        Strong programming skills in Python, PySpark, and SQL

·        Solid grounding in statistics, machine learning, experimentation, and model evaluation

·        Hands-on experience with Databricks for exploratory analysis, model development, and reproducible ML workflows; familiarity with MLflow is strongly preferred

·        Demonstrated experience with time series modeling, forecasting, anomaly detection, and/or sequential data problems

·        Experience working with IoT, sensor, telemetry, or other operational data sources

·        Strong data engineering capability, including data wrangling at scale, feature pipeline design, dataset preparation, data quality troubleshooting, and support for production-ready analytical workflows

·        Experience creating data products or analytics products intended for repeated use

·        Experience designing baselines, features, evaluation frameworks, and error analysis approaches for real-world AI/ML use cases

·        Strong ability to work across GitHub and Azure DevOps workflows, including pull requests, version control, and delivery tracking

·        Demonstrated ability to communicate clearly with technical and non-technical stakeholders and to influence product decisions with evidence

·        Experience partnering cross-functionally with engineering, product, and business teams to move from problem framing to production decision-making

Preferred Skills:

API design and integration, model monitoring, mentoring experience, familiarity with cloud-native deployment patterns

Our Commitment to a Culture of Inclusion & Belonging
Ecolab is committed to fair and equal treatment of associates and applicants and furthering the principles of Equal Opportunity to Employment. We will recruit, hire, promote, transfer and provide opportunities for advancement based on individual qualifications and job performance in all matters affecting employment, compensation, benefits, working conditions, and opportunities for advancement. Ecolab will not discriminate against any associate or applicant for employment because of race, religion, color, creed, national origin,citizenship status, sex, sexual orientation, gender identity and expressions, genetic information, marital status, age, or disability.