Data Scientist

Must have:

· 8+ years of experience in a data scientist, ML engineer, or advanced analytics role

· Strong foundation in statistics — hypothesis testing, regression, time series analysis, Bayesian methods

· Advanced SQL — comfortable writing complex queries across large, multi-source datasets

· Proficiency in Python or R for analysis, modeling, and automation

· Experience with ML/statistical libraries (scikit-learn, statsmodels, pandas, NumPy, or similar)

· Experience with AWS data and ML services (SageMaker, Redshift, Athena, Glue, QuickSight, or similar)

· Hands-on experience with Tableau

· Demonstrated ability to define metrics frameworks and build dashboards from scratch, not just maintain existing ones

· Experience building anomaly detection or predictive models in a production or operational context

· Strong communication skills — able to present statistical findings to executives, engineering leaders, and technical teams with equal clarity

· Experience working across multiple teams or systems, synthesizing data from disparate sources into a unified view

Good to have:

· Familiarity with healthcare, diagnostics, or lab operations

· Experience with operational analytics (error tracking, SLA monitoring, system health metrics)

· Experience with real-time or streaming analytics (Kinesis, Lambda)

Key role and responsibilities:

· Define and build the metrics framework for the digital ordering pipeline — from order intake through result delivery

· Design and deliver dashboards that track order volume, throughput, turnaround times, error rates, and system stability across multiple integration points

· Build predictive models to forecast order failures, volume trends, and capacity needs

· Develop automated anomaly detection to surface pipeline issues before they escalate

· Apply statistical methods for root cause analysis — diagnosing why systems fail, not just what failed

· Partner with engineering teams to instrument data collection where gaps exist

· Translate complex technical and statistical findings into clear narratives for executive leadership, engineering management, and individual engineering teams

· Investigate ad-hoc data questions — diagnosing production issues, quantifying impact of incidents, and supporting root cause analysis

· Document metric definitions, model logic, data sources, and dashboard design so the organization can maintain and extend your work independently