The posting
About Truveta
Truveta is the world's first health provider-led data platform with a vision of Saving Lives with Data. Our mission is to enable researchers to find cures faster, empower every clinician to be an expert, and help families make the most informed decisions about their care. Achieving Truveta's ambitious vision requires an incredible team of talented and inspired people with a unique combination of health, software, and big data expertise who share our company values.
Location - Hyderabad, India.
This opportunity
Join the founding team of the Truveta India Development Center and play a pivotal role in shaping its future. As one of the early members, you will help build and scale a high-impact organization while contributing to the products and platforms that advance healthcare through data and AI. This is an unusual chance to influence both the technical direction and the culture of a growing global engineering hub.
Patients, doctors, and medical researchers deserve to benefit from the large-scale technological innovation and digital intelligence that have driven progress in other industries. In this position you will build online services, automation, and tooling that monitor Truveta's data and make sure it continues to meet our high-quality standards. The work calls for creative problem solving and a strong appetite for applying AI and machine learning to anomaly detection, supported by statistical methods, to monitor and reason over big data at scale.
Who we need
We are looking for software engineers who are excited by the opportunity to improve healthcare in far-reaching ways, and who sit comfortably at the boundary between production engineering and applied machine learning. You will design and ship services rather than notebooks, and you will be expected to explain why a given detection method suits a given data problem, how you evaluated it, and what its false-alert rate costs the people who receive its alerts.
Beyond core capabilities, we are seeking problem solvers, collaborative teammates, and people willing to roll up their sleeves while making a difference. You will learn the healthcare domain quickly, because the quality of clinical data cannot be judged without understanding what the data is meant to represent.
What you will do
In this role you will:
- Build performant AI-based anomaly detection and monitoring systems, using machine learning and supporting statistical methods to analyze big data at scale.
- Design, implement, test, deploy, operate, and tune the online services, automation, and tooling that monitor Truveta's data, contributing hands-on to every stage of the software development lifecycle.
- Detect and characterize data-quality issues such as missing or late feeds, volume and distribution shifts, schema and contract drift, duplication, and implausible clinical values.
- Develop and evaluate detection approaches, from statistical baselines and time-series methods through machine-learning models, and measure them on precision, recall, and alert usefulness rather than accuracy alone.
- Turn detection output into signals people can act on: alerts with root-cause context, data-quality metrics, and dashboards that engineering and clinical teams trust.
- Work with data-processing engineers to build quality checks into pipelines so that defects are caught where they are introduced.
- Collaborate with cross-functional teams including product managers, clinical informaticists, architects, and other engineers to define what quality means for each data domain.
- Take part in design reviews, code reviews, and the on-call rotation for the services you own.
Required qualifications
- Bachelor's degree in Computer Science or a related field, or equivalent practical experience.
- 1+ of experience building production-quality services on a cloud platform such as Azure, AWS, or GCP.
- 2+ years writing Python for machine learning, AI-based data analytics, or statistical modeling.
- Hands-on experience across the software development lifecycle: design, implementation, testing, deployment, operations, and performance.
- Working knowledge of the statistics and model-evaluation methods that underpin that modeling work.
- Strong problem-solving skills and the ability to learn a new domain quickly.
- Clear written and spoken communication, and comfort collaborating across disciplines.
Preferred qualifications
- Experience developing and evaluating AI or machine-learning approaches for anomaly detection, with supporting knowledge of statistical methods, time-series analysis, or data-quality monitoring.
- Experience working as part of distributed teams, particularly 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.
- Familiarity with data-quality and observability tooling such as Great Expectations, Deequ, Soda, or equivalent in-house frameworks.
- Experience operating machine-learning models in production, including drift monitoring and retraining.
- Exposure to healthcare, clinical, or other regulated data.
