Siddharth Yadav
Software Engineer · M.S. Computer Science @ Virginia Tech
Software Engineer focused on creating robust, scalable applications and exploring the intersection of AI and software development.
About Me
I'm a Software Engineer pursuing my M.S. in Computer Science at Virginia Tech. With 5+ years of industry experience at companies like TATA AIG and Infosys, I've built everything from serverless policy management portals on AWS to retry microservices that reduced failure rates by 70%.
Currently, I'm a Graduate Research Assistant at the Commonwealth Cyber Initiative, where I'm developing LLM agent systems with MCP server integration for automated threat detection and security operations. I also interned at the American Chemical Society, where I built a GitHub PR review tool that cut manual review effort by 85%.
My sweet spot is at the intersection of AI and software engineering — building multi-agent systems, fine-tuning LLMs for code analysis, and designing cloud-native architectures on AWS.
Experience
Commonwealth Cyber Initiative
Graduate Research Assistant
Jan 2025 - Present
Arlington, VA
Developing LLM agent system with MCP server integration for security operations that provides faster log analysis with real-time SIEM integration and automated threat detection. Developed and evaluated LLM-augmented strategies for intelligent alert triage of potential phishing attacks, significantly reducing incident response times (MTTR) while maintaining high-fidelity threat detection.
American Chemical Society
Software Engineering Intern
May 2025 - Aug 2025
Washington, DC
Engineered and launched a GitHub PR review tool, automating data collection and cutting manual review effort by 85%. Leveraged the pub-sub pattern using EventBridge, AWS SQS to decouple services and handle asynchronous events within the Integration and Orchestration platform. Set up a GitHub Actions CI/CD pipeline for ACS Pubs repos, increasing deployment frequency from weekly to over 10 deployments per day.
TATA AIG General Insurance
Software Engineer
Sep 2022 - July 2024
Gurugram, India
Developed backend services of a highly scalable portal for creating and modifying policies using Lambda, RDS, NodeJS, S3, achieving a 90% improvement in TAT. Built a cross-organization report and access management platform using ReactJS, EC2 and ExpressJS, reducing report generation time by 80%. Implemented product APIs with authorization and rate limiting using AWS API Gateway, VPC, Redis.
Infosys Limited
System Engineer
Nov 2020 - Aug 2022
Mysore, India
Contributed towards efficient management of client mortgage and personal loan application platform utilizing Docker and Kubernetes, reducing infrastructure cost by 15%. Designed and implemented a retrying microservice for syncing cases to downstream leveraging Step Functions and Redis, reducing failure rate by 70%. Mentored new employees on clean code and best practices.
Projects
AI Code Review Agent
A multi-agent code review system using LangGraph with 4 parallel specialist agents (security, performance, style, test coverage) and a multi-provider LLM abstraction supporting Groq, Gemini, OpenAI, and Anthropic. Achieved 100% context precision, 86% F1 score, and 61% token savings.
Bug Localization & Repair Using LLMs
A dual-model system using fine-tuned Llama 3B Instruct for automated bug localization and repair, benchmarked against GPT-4 and Qwen Coder 32B. Demonstrated that targeted fine-tuning can outperform larger general-purpose LLMs.
Skills & Technologies
Languages
Frontend
Backend
AI / ML
DevOps & Tools
Databases
Get In Touch
I'm currently open to new opportunities and always happy to connect. Whether you have a question, a project idea, or just want to say hi — feel free to reach out.