Note: The job is a remote job and is open to candidates in USA. RIT Solutions, Inc. is hiring a Data & ML Engineer to support the person matching and identity resolution workflows of the MPI initiative, leveraging Microsoft Fabric, Synapse, and ML capabilities. This role involves creating data pipelines, cleansing and linking records, and operationalizing ML-based entity resolution models.
Responsibilities
- Build data pipelines and ML workflows within Microsoft Fabric for entity matching and deduplication across data domains
- Implement and optimize MLOps pipelines (training, scoring, and retraining)
- Integrate data from multiple sources: CRM, EHRs, finance, HR, etc
- Develop reusable modules for fuzzy matching, rule-based, and ML-based identity resolution
- Collaborate with data scientists and SMEs to operationalize models using SynapseML, PySpark, or Azure ML
Skills
- 5+ years of experience in data engineering and machine learning in the Azure ecosystem
- Proficient with Microsoft Fabric (Lakehouse, Pipelines, Notebooks), Synapse, and Azure ML
- Solid understanding of identity resolution techniques, especially ML-based approaches
- Strong programming skills in Python and PySpark
- Familiarity with data privacy, governance, and ethics in ML
Benefits
- Work_model: [remote]
Company Overview
Company H1B Sponsorship