Machine Learning Engineer II

Machine Learning Engineer II, Hyderabad

As a Machine Learning Engineer II on the Hyderabad SPARK team, you will be a hands-on builder of production ML systems across WBD s consumer platforms. You will translate data science ideas into reliable pipelines, models, and services that support identity, audience intelligence, advertising, personalization, forecasting, engagement, and retention use cases.

You will work closely with senior engineers, data scientists, product managers, and platform teams to build reproducible ML workflows, improve model quality, and help operate models with strong monitoring, governance, and production-readiness practices.

What You ll Do

Technical Execution & Delivery

• Build and operate low-latency online serving systems for fraud scoring, message decisioning, and real-time personalization.
• Develop ML models for identity resolution, audience intelligence, content-affinity modeling, genre-preference modeling, and time-series forecasting across global markets.
• Integrate with personalization and activation systems to consume in-app user signals and deliver model outputs into downstream workflows.
• Implement feature pipelines that combine real-time streaming signals with batch-computed features for online scoring.
• Partner with Product, Engineering, and Data Science to translate business problems into well-scoped ML solutions.
• Contributes to evaluations of new technologies and approaches, including DCR-native modeling, graph ML, agentic ML orchestration, and LLM-augmented pipelines.

Production ML Systems

• Build and improve probabilistic identity resolution components that connect unauthenticated device IDs and first-party cookies to households/persons with calibrated confidence across WBD brands.
• Contribute to Audience Intelligence capabilities, including ML Promo Optimizer, STAT v2, lookalike modeling inside Snowflake DCR, and content segmentation.
• Develop and productionize forecasting models for use cases such as audience growth, demand, yield, and pricing, ensuring models are monitored and continuously improved.
• Bring ML personalization signals, such as genre/content affinity and engagement trends, into batch and future real-time activation paths.
• Implement MLOps workflows for experiment tracking, model versioning, deployment automation, retraining, monitoring, and drift detection.

Experimentation, Quality & Observability

• Implement offline and online evaluation approaches with clear baselines, success metrics, experiment design, and promotion criteria.
• Improve feature and label quality, leakage prevention, bias checks, calibration, explainability where applicable, and impact measurement.
• Identify technical risks early, document tradeoffs, and partner with engineering, data, product, and business stakeholders on mitigation plans.
• Turn incidents and postmortems into reusable learnings, automated checks, and platform improvements.
• Apply production-readiness practices such as testability, data quality checks, rollback paths, drift monitoring, and dashboards.

Cross-functional Partnership & Mentorship

• Partner with ML leads on execution planning, technical design, capability development, and delivery of production ML systems.
• Represent the Hyderabad team in technical discussions with ML, Data Engineering, Product, Ad Sales, and US-based stakeholders.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.