Role Overview
Join the founding team of Truveta India Development Center to build AI-based anomaly detection and monitoring systems for healthcare data quality. You will design and operate production services that detect data-quality issues using machine learning and statistical methods at scale.
Responsibilities
- Build performant AI-based anomaly detection and monitoring systems using ML and statistical methods to analyze big data at scale.
- Design, implement, test, deploy, operate, and tune online services, automation, and tooling that monitor Truveta's data.
- Detect and characterize data-quality issues: missing/late feeds, volume/distribution shifts, schema drift, duplication, implausible clinical values.
- Develop and evaluate detection approaches from statistical baselines through ML models, measuring precision, recall, and alert usefulness.
- Turn detection output into actionable signals: alerts with root-cause context, data-quality metrics, and trusted dashboards.
- Collaborate with data-processing engineers to embed quality checks into pipelines.
- Work cross-functionally with product managers, clinical informaticists, architects, and engineers to define quality per data domain.
- Participate in design reviews, code reviews, and on-call rotation for owned services.
Requirements
- Bachelor's degree in Computer Science or related field, or equivalent practical experience.
- 1+ years building production-quality services on a cloud platform (Azure, AWS, or GCP).
- 2+ years writing Python for machine learning, AI-based data analytics, or statistical modeling.
- Hands-on experience across the full software development lifecycle: design, implementation, testing, deployment, operations, performance.
- Working knowledge of statistics and model-evaluation methods underpinning modeling work.
- Strong problem-solving skills and ability to learn a new domain quickly.
- Clear written and spoken communication, comfort collaborating across disciplines.
Nice to Have
- Experience developing and evaluating AI/ML approaches for anomaly detection with statistical methods, time-series analysis, or data-quality monitoring.
- Experience working in distributed teams across India and the United States.
- Experience processing large datasets with Spark, Databricks, or comparable distributed frameworks, and strong SQL.
- Experience running services on Microsoft Azure.