Aryan Dokania

About Aryan Dokania

I\'m a Master\'s student in Computer Science at UC San Diego, specializing in AI/ML systems. Currently a Software Engineering II Intern at Cisco (Duo Security), where I\'m building LLM-based code review systems using AWS Bedrock Claude. My expertise spans AI agents, machine learning, and cloud infrastructure. At Oracle, I led critical system migrations including MySQL upgrades that doubled replication speed, containerized services with Docker/Kubernetes reducing migration time by 50%, and automated CI/CD pipelines that cut deployment time by 90%. I\'ve also optimized distributed systems performance, reducing signaling latency in VoLTE networks during peak loads. I specialize in building scalable, fault-tolerant systems using Go, Python, C++, and Java. My recent projects include distributed video streaming platforms with MPEG-DASH on AWS, intelligent gRPC load balancers that reduced tail latency by 35%, and LLM-powered JIRA search tools using fine-tuned LLaMA models. Passionate about solving complex engineering challenges at the intersection of AI, distributed systems, and cloud infrastructure. Always looking to build systems that are efficient, reliable, and built to scale.

Experience

1. Software Engineer Ii Intern

   Cisco

   Jun 2025 — Present · Ann Arbor, MI, US

   Fine-tuning large language models (LLM) for ai code review, with a focus on improving accuracy, contextual relevance, and seamless integration into developer workflows.• Built a logistic regression classifier on SBERT embeddings to evaluate LLM-generated code reviews, improving F1 score by 15% through data augmentation and hyperparameter tuning

Education

• Vellore Institute of Technology

  Bachelor of Technology - BTech, Computer Science and Engineering

  2023

• UC San Diego

  Master of Science - MS, Computer Science