Rahul Yadav

Results-driven Data/ML Engineer with 2.5+ years of expertise in designing and deploying scalable data pipelines, realtime streaming architectures, and ML systems. Proficient in Apache Spark, Kafka, Flink, Python, and cloud platforms with a proven track record in ETL optimization, MLOps, and distributed computing. Strong collaboration and problemsolving skills with experience delivering high-impact solutions across cross-functional teams.

Data/ML Engineer - Jio Platforms Limited - Mumbai, India

(2023-12)

• Architected and deployed LightGBM-based CTR prediction system processing 300M+ daily impressions, achieving 15% accuracy improvement through advanced feature engineering and hyperparameter optimization
• Engineered real-time streaming pipelines using Apache Kafka and Flink for low-latency feature computation, enabling sub-second analytics for campaign optimization
• Migration ETL Job from Spark to Flink, reducing end-to-end latency by 40% while collaborating with infrastructure and analytics teams for seamless deployment
• Optimized distributed PySpark and Scala jobs through partitioning, broadcast joins, and caching, cutting infrastructure costs by 30%
• Designed Apache Druid OLAP datasets powering Real Time Analytic dashboards with sub-second analytical queries for real-time business intelligence
• Developed FastAPI and Flask microservices for ML model inference and monitoring, ensuring 99.9% uptime with MLOps best practices
• Orchestrated 100 TB data migration from HDFS to GCS Bucket with zero downtime, implementing automated validation pipelines for data integrity
• Implemented Great Expectations framework and Apache Airflow DAGs for robust ETL workflows, reducing data anomalies by 35%
• Partnered with analytics, product, and business stakeholders to translate requirements into technical solutions and drive campaign performance improvements

B.Tech - Electronics and Communication Engineering - Haldia Institute of Technology, Haldia, West Bengal (2019 - 2023)