Datta Sai Adithya Vinjamuri

Camarillo,USA

Summary

Analytical Computer Science graduate with hands-on experience in building and deploying machine learning applications. Skilled in Python, scikit-learn, TensorFlow, and AWS cloud tools. Demonstrated expertise in end-to-end project development, from data preprocessing to model deployment, driving impactful ML solutions in data-driven environments.

Overview

years of professional experience

Work History

Student Assistant

CSUCI

Camarillo, USA

04.2024 - 12.2025

Developed AI transcript analyzer with chat interface using ML model trained on assist.org data, reducing manual transcript inspection by 85%.
Supported the development a AI Chabot for our department through prompt engineering. Reduced unnecessary emails, phone calls by 35% in 4 months.
Delivered customer service to students and staff at front desk, addressing inquiries and managing approximately 30 incoming calls and emails daily.
Facilitated recruitment of new student assistants to enhance support for department operations.

ML Intern

Trillion IT services Pvt Ltd

Hyderabad, Telangana

01.2022 - 08.2023

Built an ML model integrated into a client web application, improving user engagement by 25%.
Developed and deployed AI-powered web features with Python, FastAPI, and React, enhancing user experience.
Designed RESTful APIs for real-time AI predictions, facilitating seamless integration with client applications.
Automated data workflows, increasing reporting accuracy and minimizing manual processing time.
Assisted in cloud deployment and CI/CD pipeline setup.

Education

Master of Science - Computer Science

California State University, Channel Islands

Camarillo, CA

12.2025

Bachelor of Science - Computer Science And Engineering

Lovely Professional University

Phagwara, Punjab, India

08.2023

Skills

Web & Mobile Development: Flask, React/Nextjs, HTML/CSS, React Native, Expo, bcrypt authentication, API development
Programming & Frameworks: Python(tensorflow, pandas, sklearn), JavaScript, SQL
Cloud & Platforms: AWS, GCP, Microsoft Office 365

Data analysis: Python, PowerBI, Tableau
DevOps & Tools: Docker, containerization, CI/CD, Version Control
Scripting & Automation: APScheduler, Scripting PowerShell

Projects

AI-Powered Penetration Testing Platform: Comprehensive full-stack cybersecurity application combining Nmap, OWASP ZAP & SQLMap orchestration with advanced AI analysis (Google Gemini 1.5 Pro). Built on a Python Flask backend in a Docker-containerized microservices architecture.

AI Integration: Gemini-driven scan analysis, risk assessment & Q&A with caching & rate limiting
Machine Learning: Random Forest model for automated risk scoring
Real-time CVE Monitoring: NVD API fetcher for up-to-date vulnerability intelligence
Reporting: Automated PDF/HTML/JSON report generation with professional styling & data visualization
Security & Scheduling: Bcrypt auth, session management, secure API keys; APScheduler-powered cron scans with DB persistence & management UI.
Kali Linux Integration: Embedded terminal environment for hands-on testing.
Full tech Architecture: Python, Flask, Docker, SQLite, NLTK, scikit-learn, Google Gemini API, OWASP ZAP, Nmap, SQLMap, Kali Linux, HTML/CSS/JavaScript.

Network Anomaly Detection System: Intelligent full-stack monitoring application that identifies real-time network anomalies using unsupervised machine learning. Built with a Python Flask backend, ML-driven detection engine, and containerized deployment architecture.

Unsupervised ML Detection: Utilizes Isolation Forest (Scikit-Learn) to analyze multi-dimensional telemetry data (CPU usage, latency, throughput), detecting zero-day lag spikes and anomalies with 99.7% accuracy.
High-Throughput Processing Engine: Designed with Pandas and NumPy to simulate, profile, and evaluate over 76,000 requests per second for performance stress testing and anomaly scoring.
Secure REST API & Alerting: Developed a Flask-based REST API secured with Bcrypt authentication, integrated with an automated alerting system that simulates AWS SNS triggers when threat-confidence scores exceed 80%.
Containerized Microservice Architecture: Deployed using Docker and Docker Compose, orchestrating the ML detection service with locally mapped volumes for isolated, zero-dependency execution.
Full-Stack Architecture: Python, Flask, Scikit-Learn, Pandas, NumPy, Docker, Docker Compose, Bcrypt

Related Course Work

AWS Academy Cloud Developing, 2024, S3, IAM, Lambda, API Gateway, DynamoDB, Elastic Beanstalk, ECS, ElastiCache, CloudFront, SNS/SQS, Kinesis, CI/CD (CloudFormation, SAM)
AWS Academy Machine Learning Foundations, 2025, SageMaker pipelines, Autopilot, Forecast, Rekognition, Comprehend, Polly, Translate, Lex, Amazon Q Developer (gen-AI)

Timeline