Languages
& Query
•
SQL- data profiling, validation rules, quality checks, large-scale dataset
analysis
• Python - automation, ML/AI
techniques, scripting, pipeline development
Data Quality & Governance
• Data quality frameworks
(Great Expectations, dbt tests) augmented with ML/LLM
• Data governance practices
(metadata management, lineage review, issue tracking)
• Data stewardship,
remediation workflows, and automated quality monitoring pipelines
• Data lineage and impact
analysis
• Data completeness and
reliability measurement
ML/AI for Data Quality
• Supervised learning -
classification models to flag bad records (e.g., mislabeled diagnosis codes,
incorrect attributions)
• Unsupervised learning -
clustering to detect outliers, unusual patterns, and grouping anomalies in
clinical data
• Anomaly detection -
model-driven (Isolation Forest, LOF, One-Class SVM)
• Data drift monitoring -
statistical process control (KS test, PSI, Jensen-Shannon divergence)
• NLP / Text Analytics -
parsing unstructured clinical notes, extracting entities, detecting coding
inconsistencies
• Record linkage / Entity
resolution - ML-based deduplication using probabilistic matching (e.g., patient
matching across systems)
• Pattern recognition and
root cause analysis
AI Frameworks & Libraries
• scikit-learn - anomaly
detection, clustering, classification
• PyOD - outlier detection
• TensorFlow / PyTorch - deep
learning for complex pattern recognition in large clinical datasets
• LLMs (GPT, Claude, etc.) -
automated root cause summarization, natural language quality reports, code
review assistance
Dash boarding & Reporting
• Alerting and monitoring
dashboards (Tableau, Power BI, Streamlit, or similar)
• Data quality trend reporting and
operational risk communication
Healthcare Domain Knowledge
• Healthcare coding systems (ICD,
CPT, HCPCS)
• Member attribution logic
• Clinical quality measures
(HEDIS, Stars)
• Interoperability data (HL7,
FHIR)
•
Payer/provider/clinical/population health datasets
Skills Required
- SQL for data profiling, validation rules, quality checks, and large-scale dataset analysis
- Python for automation, scripting, machine learning techniques, and pipeline development
- Experience with data quality frameworks such as Great Expectations and dbt tests
- Knowledge of data governance, metadata management, data lineage, impact analysis, and issue tracking
- Experience with data stewardship, remediation workflows, and automated quality monitoring
- Knowledge of supervised learning, unsupervised learning, anomaly detection, data drift monitoring, NLP, and entity resolution
- Experience with scikit-learn, PyOD, TensorFlow, or PyTorch
- Experience building alerting, monitoring, and reporting dashboards using Tableau, Power BI, Streamlit, or similar tools
- Knowledge of healthcare coding systems, including ICD, CPT, and HCPCS
- Knowledge of HEDIS, Stars, member attribution, HL7, FHIR, and healthcare datasets
What We Do
Blackbuck Insights is a global data and AI consultancy providing data engineering services, cloud modernization, AI activation, and platform operations. The company helps enterprises modernize legacy environments, migrate and scale data platforms, build AI-enabled business applications, and establish trusted data foundations for analytics and intelligent decision-making. Its services support organizations seeking reliable, performant, and scalable technology solutions.
