RV
Initializing Portfolio
Open to Full-Time Roles · May 2026
VJIT Hyderabad · B.Tech CS & Data Science · Class of 2026

RAGHU
VARDHAN

AI Engineer ML Engineer Data Scientist Full-Stack QA Automation

Building production-grade AI systems from LLM routers to enterprise RAG pipelines.
10 shipped projects · 97% cost reduction · GPA 8.1

0
Projects Shipped
97%
Cost Reduction
8.1
GPA · B.Tech
4+
Certifications
View Projects ↗ GitHub Profile
Scroll Down
Production RAG
LLM Fine-Tuning
FastAPI · React 18
ChromaDB · pgvector
Python · Scikit-learn
Selenium · pytest
Claude API · OpenAI
LoRA · QLoRA · PEFT
SQL · Data Engineering
Grafana · FastAPI
Production RAG
LLM Fine-Tuning
FastAPI · React 18
ChromaDB · pgvector
Python · Scikit-learn
Selenium · pytest
Claude API · OpenAI
LoRA · QLoRA · PEFT
SQL · Data Engineering
Grafana · FastAPI
01

ABOUT

I'm a final-year B.Tech Computer Science & Data Science student at Vidya Jyothi Institute of Technology, Hyderabad — graduating May 2026 with a GPA of 8.1.


I've shipped 10 production-grade projects spanning enterprise RAG pipelines, LLM fine-tuning systems, full-stack AI analytics platforms, machine learning pipelines, and QA automation frameworks — work that would conventionally take months, delivered with precision and measurable impact.


My philosophy: AI is a force multiplier, not a shortcut. I've engineered LLM routers that cut API costs by 81%, synthetic data pipelines that fine-tune models at 97% lower inference cost, and production RAG systems with PII guardrails, confidence scoring, and Docker deployment — all as a fresher.


Actively seeking entry-level roles in AI Engineering, Data Science, Software Engineering, and QA Automation.

Education
B.Tech CS & Data Science
VJIT Hyderabad · GPA 8.1
Diploma CSE · TRR College · GPA 7.0
Location
Hyderabad, Telangana
Open to Relocation Anywhere
Availability
May 2026 · Full-Time Roles
02

PROJECTS

02
AI / LLM

LLM EVAL
DASHBOARD

PRODUCTION BENCHMARK PLATFORM

Benchmarks LLM outputs across quality, cost, latency, and hallucination rate with a live Grafana dashboard and FastAPI backend. Compare models side-by-side with real-time metrics.

Python FastAPI Grafana LLM Eval
View on GitHub
03
AI / LLM

DOMAIN FINE-
TUNE API

LoRA / QLoRA FINE-TUNING PLATFORM

Fine-tunes open-source LLMs (Mistral-7B, LLaMA-3) on domain-specific data using LoRA/QLoRA. Full dataset manager, training dashboard, benchmark comparison, and inference playground.

JavaScript LoRA/QLoRA Mistral-7B LLaMA-3 HuggingFace
View on GitHub
04
AI / LLM

SYNTHETIC DATA
FACTORY

97% LOWER INFERENCE COST

Uses a large LLM as teacher to generate training data, then fine-tunes a tiny model via LoRA/PEFT+TRL on Phi-3-mini with 4-bit quantization — the tiny model beats the large one at 97% lower cost.

97%
Cost Reduction
+73.7%
ROUGE-L vs GPT-4o
Python PEFT / TRL Phi-3-mini Claude API LoRA HuggingFace
View on GitHub
05
AI / LLM

LLM ROUTER
PROMPT GATEWAY

SYSTEM 1 VS SYSTEM 2 ROUTING · 81% COST CUT

Scores prompts across 7 weighted complexity dimensions, auto-routing simple tasks to cheap/fast models and complex reasoning to premium ones. Supports Anthropic + OpenAI interchangeably. Zero accuracy tradeoff.

81%
API Cost Reduction
7
Complexity Dims
Python Claude API OpenAI NLP Cost Engineering
View on GitHub
06
Full-Stack AI

WIKIMIND
KNOWLEDGE BASE

PRODUCTION RAG · REACT 18 + FASTAPI

Full production RAG pipeline: 512-token semantic chunking → all-MiniLM-L6-v2 embeddings → ChromaDB retrieval → Claude API with citations. Async FastAPI + SSE streaming + React 18 frontend with drag-and-drop, live token streaming, and relevance scores.

Python RAG ChromaDB FastAPI React 18 SSE Streaming Claude API
View on GitHub
07
Full-Stack

SMARTCART
INTELLIGENCE

AI E-COMMERCE ANALYTICS PLATFORM

Full-stack data science platform over 8,000+ synthetic orders: Random Forest churn (AUC 0.658), Gradient Boosting revenue forecast, Apriori market basket, Claude API as natural language Business Analyst, and 10 optimised SQL queries powering real-time KPI cards.

Python Random Forest Claude API SQLite Apriori ML Analytics
View on GitHub
08
Machine Learning

CUSTOMER CHURN
PREDICTION

END-TO-END ML PIPELINE · ROC-AUC 0.754

3-model pipeline on 5,000 telecom records with full feature engineering. Best ROC-AUC 0.754 with Gradient Boosting. SHAP-style importance analysis. Fully reproducible EDA-to-deployment pipeline in scikit-learn.

0.754
ROC-AUC Score
5K
Records Analyzed
Scikit-learn XGBoost SHAP Seaborn SMOTE Python
View on GitHub
09
Data Engineering

HR EMPLOYEE
SQL ANALYSIS

RELATIONAL DATA ENGINEERING · 17 QUERIES

Fully normalised 4-table relational schema with 17 analytical queries — JOINs, correlated subqueries, RANK/DENSE_RANK window functions, CASE WHEN logic. Python-SQLite execution layer auto-generates 5 Matplotlib charts.

17
Analytical Queries
4
Normalised Tables
SQL MySQL Python-SQLite Matplotlib Window Functions
View on GitHub
10
Data Analytics

GLOBAL COVID-19
EDA

MULTI-COUNTRY PANDEMIC ANALYTICS

Structured EDA across 20 countries and 36 months, engineering 5 publication-quality visualisations covering case trajectories, vaccination rollout impact, regional death-rate disparities, and socioeconomic correlations.

20
Countries Analyzed
36
Months of Data
Python Pandas Matplotlib Plotly EDA Seaborn
View on GitHub
03

SKILLS

AI / LLM
LLM Integration & Prompt Eng.
94%
RAG Pipelines
90%
LoRA / PEFT Fine-Tuning
85%
Claude / OpenAI APIs
92%
Vector DBs (Chroma, pgvector)
88%
Python & ML
Python · Pandas · NumPy
92%
Scikit-learn · XGBoost
85%
SQL · MySQL · Data Eng.
88%
FastAPI · Async Python
82%
Matplotlib · Plotly · Seaborn
84%
Frontend & QA
React 18 · JavaScript
80%
HTML · CSS · Vite
78%
Selenium · pytest
82%
Docker · Git · Linux
76%
Power BI · Grafana
72%
CS
Data Analytics Essentials
Cisco · Verified
CS
Python Essentials 1 & 2
Cisco · Verified
OR
Data Analysis & Advanced AI
Oracle · Verified
OR
Oracle AI Foundations
Oracle · Verified
04

CONTACT

Open to full-time roles in Data Science, AI Engineering, Software Engineering & QA Automation. Based in Hyderabad — open to relocation anywhere.