Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Sravani Chowdary Kasaraneni, an AI/ML Engineer focused on building real-time machine learning systems for fraud detection and personalization. Over 4+ years, I have designed low-latency models, engineered large-scale features, and tuned precision-recall to perform in high-volume transaction environments. I thrive on turning streaming data into actionable decisions that improve accuracy and reliability while reducing manual workload.\n\nIn production, I integrate ML models into Kafka and Spark streaming pipelines, monitor drift, and maintain end-to-end lifecycles from feature engineering to deployment. I enjoy collaborating with fraud strategy and operations teams to refine alert prioritization and decision workflows for fast, reliable incident response.…I'm Sravani Chowdary Kasaraneni, an AI/ML Engineer focused on building real-time machine learning systems for fraud detection and personalization. Over 4+ years, I have designed low-latency models, engineered large-scale features, and tuned precision-recall to perform in high-volume transaction environments. I thrive on turning streaming data into actionable decisions that improve accuracy and reliability while reducing manual workload.\n\nIn production, I integrate ML models into Kafka and Spark streaming pipelines, monitor drift, and maintain end-to-end lifecycles from feature engineering to deployment. I enjoy collaborating with fraud strategy and operations teams to refine alert prioritization and decision workflows for fast, reliable incident response.

Sravani Chowdary Kasaraneni

Data Scientist, AI Engineer, Full Stack Developer, +2





I'm Sravani Chowdary Kasaraneni, an AI/ML Engineer focused on building real-time machine learning systems for fraud detection and personalization. Over 4+ years, I have designed low-latency models, engineered large-scale features, and tuned precision-recall to perform in high-volume transaction environments. I thrive on turning streaming data into actionable decisions that improve accuracy and reliability while reducing manual workload.\n\nIn production, I integrate ML models into Kafka and Spark streaming pipelines, monitor drift, and maintain end-to-end lifecycles from feature engineering to deployment. I enjoy collaborating with fraud strategy and operations teams to refine alert prioritization and decision workflows for fast, reliable incident response.…I'm Sravani Chowdary Kasaraneni, an AI/ML Engineer focused on building real-time machine learning systems for fraud detection and personalization. Over 4+ years, I have designed low-latency models, engineered large-scale features, and tuned precision-recall to perform in high-volume transaction environments. I thrive on turning streaming data into actionable decisions that improve accuracy and reliability while reducing manual workload.\n\nIn production, I integrate ML models into Kafka and Spark streaming pipelines, monitor drift, and maintain end-to-end lifecycles from feature engineering to deployment. I enjoy collaborating with fraud strategy and operations teams to refine alert prioritization and decision workflows for fast, reliable incident response.

Available to hire

I’m Sravani Chowdary Kasaraneni, an AI/ML Engineer focused on building real-time machine learning systems for fraud detection and personalization. Over 4+ years, I have designed low-latency models, engineered large-scale features, and tuned precision-recall to perform in high-volume transaction environments. I thrive on turning streaming data into actionable decisions that improve accuracy and reliability while reducing manual workload.\n\nIn production, I integrate ML models into Kafka and Spark streaming pipelines, monitor drift, and maintain end-to-end lifecycles from feature engineering to deployment. I enjoy collaborating with fraud strategy and operations teams to refine alert prioritization and decision workflows for fast, reliable incident response.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Work Experience

AI/ML Engineer at JPMorgan Chase & Co.

July 1, 2024 - Present

Built and productionized fraud detection models for real-time payment authorization systems, improving detection performance by 15% in high-risk transaction segments while meeting strict sub-100ms latency requirements. Reduced false positives by 20% in high-volume card transactions through threshold tuning, feature engineering, and decision policy calibration, improving alert precision without impacting recall in critical fraud scenarios. Engineered high-signal behavioral and transactional features using PySpark on large-scale datasets, improving model robustness and reducing feature computation latency. Integrated model inference into Kafka and Spark-based streaming pipelines, enabling near real-time fraud scoring within a production environment processing millions of transactions daily. Designed risk-aligned thresholds under severe class imbalance, improving fraud capture quality while reducing unnecessary case escalation. Owned end-to-end fraud detection model lifecycle from feature

ML Engineer at Neon IT Systems, India

January 1, 2020 - November 1, 2022

Developed and deployed machine learning models for personalization and ranking systems, improving recommendation relevance and optimizing metrics through iterative experimentation. Designed scalable inference pipelines for batch and near real-time workloads, improving latency and throughput. Engineered feature pipelines on large-scale datasets using behavioral signals, improving model stability across user segments. Built backend services for ML workflows and owned deployment and monitoring to ensure long-term reliability; contributed to CI/CD and infrastructure automation.

ML Engineer at Neon IT Systems

January 1, 2020 - November 1, 2022

Developed and deployed machine learning models for personalization and ranking systems, improving recommendation relevance through iterative experimentation and metric-driven optimization. Designed scalable model inference pipelines for batch and near real-time workloads, improving latency and throughput. Engineered feature pipelines on large-scale datasets using behavioral and interaction signals, improving model stability. Conducted structured model evaluation and error analysis, improving model quality through continuous experimentation and tuning. Built backend services for ML workflows using Python, enabling reliable model serving and asynchronous processing. Owned model deployment and monitoring workflows, implementing data validation, drift detection, and performance tracking to maintain long-term production reliability. Contributed to CI/CD and infrastructure automation using containerization tools, improving deployment reliability and reducing manual intervention.