Raghav Narula

Meta

I work on large-scale storage infrastructure powering distributed systems and GPU workloads. My focus is on reliability, automation, and scaling storage systems across multi-cloud environments.

• Helped reduce server onboarding time from weeks to days by improving automation workflows
• Worked on scaling distributed storage systems handling petabyte-scale datasets
• Built tooling in C++ to improve cluster performance and workload efficiency

Intel Corporation

Worked on internal engineering tools used by large teams to manage and process production data.

• Improved performance of internal desktop tools significantly through parallel processing
• Modernized legacy applications used across engineering workflows

Attentive.ai

Built backend systems and automation tools to improve testing and monitoring pipelines.

• Developed pipeline orchestration system improving service efficiency
• Automated testing workflows, reducing manual effort substantially
• Built real-time monitoring dashboards for system health tracking

Concordia University

Worked on deep learning models for transportation systems and published research in IEEE.

• Built ML model for predicting passenger flow in transit systems
• Published research in IEEE Xplore
• Improved prediction accuracy over baseline models

Monocular Odometry Vision

TensorFlow-based model (2.5M params) for robot odometry prediction

Published Research →

Passenger Flow Prediction

Deep learning model for transit systems

IEEE Xplore Publication →

What I explore outside work

• Studying distributed systems failures and real-world outages
• Reading AWS / Google / Meta postmortems
• Building low-level performance tools in C++
• Exploring system design and scaling patterns