ASG
Available for Opportunities · May 2026

Adithya
Santhosh
Gaddam

AI/ML Engineer  ·  Full-Stack  ·  Cloud & DevOps

M.S. Computer Science candidate at Texas A&M–San Antonio building production-grade AI systems, RAG pipelines, and cloud-deployed platforms. Turning ideas into intelligent applications.

View My Work → Get in Touch
LangChain FastAPI ChromaDB Docker HuggingFace PyTorch AWS PySpark RAG FAISS
8+
Projects Shipped
6+
Certifications
M.S.
CS — May 2026
100+
Workshop Attendees
About Me

Building the intelligent future

I'm a M.S. Computer Science candidate at Texas A&M University–San Antonio (graduating May 2026), deeply passionate about the intersection of AI, cloud infrastructure, and software engineering.

I build RAG pipelines, deploy LLM-powered applications, and architect scalable backends — from ChromaDB vector stores to PySpark fraud detection systems. I've completed virtual internships with Deloitte, JPMorgan Chase, and Wells Fargo.

I'm an active user of AI-assisted development tools (Claude, GitHub Copilot, Cursor) and have led cybersecurity and Arduino workshops for 100+ participants at TAMUSA.

📍 San Antonio, TX  ·  📧 Adithyasanthosh23@gmail.com

🎓
Texas A&M University – San Antonio M.S. Computer Science · 2024–2026
🤖
AI / ML Engineering LangChain · RAG · HuggingFace · PyTorch
☁️
Cloud & DevOps AWS · GCP · Docker · Kubernetes · CI/CD
💻
Full-Stack Development FastAPI · Python · React · Streamlit · SQL
🔗
GitHub github.com/adi232323
Experience

Where I've contributed

Jun 2025
Deloitte Australia (Forage)
Data Analytics Virtual Intern
  • Built Tableau dashboards and Excel financial models for forensic compliance investigations; delivered structured data findings to stakeholders.
  • Designed end-to-end analytical pipelines with validation checkpoints, repeatable workflows, and compliance-aligned documentation.
2025
JPMorgan Chase & Wells Fargo (Forage)
Software Engineering Virtual Intern
  • Completed backend engineering simulations involving REST API design, data pipelines, and agile development workflows.
  • Practiced TDD, iterative code delivery, and cross-team collaboration across structured multi-sprint engineering simulations.
2024–Now
Texas A&M University – San Antonio
Graduate Researcher & Workshop Lead
  • Led cybersecurity and Arduino workshops for 100+ participants at TAMUSA campus.
  • Presented original ML and security research at university seminars to mixed technical and non-technical audiences.
Projects

Things I've built

📄
RAG PDF Chatbot
Full-stack AI chatbot that ingests PDFs, chunks & embeds text into ChromaDB, and answers questions via a local HuggingFace LLM RAG pipeline.
PythonLangChainFastAPIChromaDBHuggingFace
View on GitHub →
🏫
TAMUSA Policy Assistant
Domain-specific RAG assistant answering university policy questions exclusively from official documents, reducing hallucinations vs. general-purpose LLMs.
LangChainFAISSGroq APIStreamlitHuggingFace
View on GitHub →
📊
Retail Demand Forecasting Platform
End-to-end forecasting platform: data ingestion → model training → evaluation → Power BI dashboard with Docker containerization for reproducible deployment.
PythonSQLREST APIsDockerPower BI
View on GitHub →
🚌
Real-Time Bus Tracking System
Full-stack real-time tracking backend with relational SQL and REST APIs; optimized query performance under concurrent, high-frequency traffic.
SQLREST APIsBackend Engineering
🔐
Credit Card Fraud Detection
Distributed fraud detection system on real transaction data using PySpark; containerized with Docker and validated with TDD-style iterative model evaluation.
PySparkPythonDockerML
⚙️
CI/CD Security Automation — Rust
Fully automated multi-tool CI pipeline (Rustc, Clippy, Cargo Audit, Geiger) with modular Python/Bash scripts; idempotent execution on Ubuntu Linux.
BashPythonLinuxRustCI/CD
🔍
Code Property Graph Vulnerability Analysis
CPG-based static analysis on Java codebases using Joern and Neo4j to detect CVE-class vulnerabilities with automated defect reporting.
PythonJoernNeo4jSecurity
🧪
LLM Code Quality Benchmarking
Reproducible benchmark suite comparing GPT-4, Gemini, and Grok against human-written algorithms; profiled per-model time complexity and memory footprint.
PythonPyTorchPerformance TestingResearch
Skills

My toolkit

AI & Machine Learning
LangChainFAISSChromaDBHuggingFaceGroq APIRAG SystemsScikit-learnPyTorchPandasNumPy
Backend & APIs
PythonFastAPIJavaC++CSQLREST API DesignJSONNode.jsPySpark
Frontend
HTMLCSSJavaScriptStreamlitReactTableauMatplotlibSeabornPower BI
Cloud & DevOps
AWSGCPDockerKubernetesGitCI/CD PipelinesGitHub Actions
Databases
SQL ServerChromaDBFAISSNeo4jRelational DB DesignQuery Optimization
Security & Analysis
JoernCargo AuditStatic AnalysisCVE TestingGraph Vulnerability Detection
Certifications

Always learning

🏆
AWS Educate: Machine Learning Foundations Amazon Web Services · Jun 2025
🤖
Generative AI with AWS Udacity · May 2025
✦
Introduction to Agent Skills Anthropic · 2025
📊
Data Analytics Simulation Deloitte Australia (Forage) · Jun 2025
💼
Software Engineering Simulations JPMorgan Chase & Wells Fargo (Forage) · 2025
🐍
Python for Everybody Coursera · Feb 2025
Get In Touch

Let's build something great

I'm actively looking for roles in AI Engineering, Software Engineering, Cloud/DevOps, and Data Engineering starting May 2026.

Adithyasanthosh23@gmail.com
LinkedIn GitHub 📞 (214) 899-0596 📍 San Antonio, TX