AVAILABLE FOR HIRE
MS DATA SCIENCE · SEATTLE U · 2026

SanjayRameshKannan

Extracting signal from noise — RAG pipelines, neural networks, and ML systems beyond notebooks.

PROJECTS
5+
ML ACCURACY
88%
RAG P@1
81.5%
LOCATION
SEA·US
Sanjay Ramesh Kannan
ABOUT ME● LIVE
MACHINE LEARNING RAG SYSTEMS NEURAL NETWORKS DATA SCIENCE PYTHON PYTORCH SQL QDRANT SCIKIT-LEARN COMPUTER VISION NLP DEEP LEARNING MACHINE LEARNING RAG SYSTEMS NEURAL NETWORKS DATA SCIENCE PYTHON PYTORCH SQL QDRANT SCIKIT-LEARN COMPUTER VISION NLP DEEP LEARNING

// 001 — CAPABILITIES

SkillSet

DOMAINS 8
EXP 3+ yrs via coursework
Machine Learning:scikit-learnRegressionClassificationSVMsEnsemble MethodsFeature EngineeringModel Evaluation
AI & LLMs:OpenAI APIPrompt EngineeringRAGSHAPLIMENLPVector Search
Data & Statistics:PythonpandasNumPySQLRHypothesis TestingCross Validation
Visualization:TableauPower BImatplotlibseabornAltairExcelBI Dashboards
Data Engineering:AWSPySparkHadoopDockerETLGitData Modeling
Deep Learning:PyTorchOpenCVCNNArcGIS ProSpatial DataAudio ML
Cloud & APIs:AWS LambdaEventBridgeS3FastAPIVercelDocker
Analytics Infrastructure:AthenaDynamoDBS3Query PipelinesData WorkflowsCloud Integrations

// 002 — SYSTEMS

Systems

TOTAL 4
ACTIVE 4
SYSTEM 01
Document Access / Tracking
SECURE SYSTEM

Resume Access System

Controlled resume distribution with secure access, dynamic watermarking, and analytics.

Next.jsAWS S3DynamoDBResendWatermarkingAnalytics
  • Time-limited signed URLs for controlled access
  • Dynamic watermarking per request using email, company, and timestamp
  • Resume request tracking with private analytics dashboard
SYSTEM 02
AI / NLP
RAG SYSTEM

Football Injury RAG System

RAG pipeline combining GPS tracking, PubMed research, and player history for injury risk prediction across structured and unstructured sources.

PythonQdrantRAGPubMed APIGPS MetricsVector Search
  • Integrated multi-source retrieval across GPS, research, and player history data
  • Engineered vector search pipeline across 50K+ points
  • Improved retrieval quality through embedding and ranking optimization
SYSTEM 03
Prediction / Simulation
MOTORSPORT ML

F1 Prediction System

End-to-end ML system for predicting race outcomes using historical and live data, simulation logic, and serverless scheduling.

PythonFastF1Monte CarloAWS LambdaEventBridgeDashboard
  • Scheduled inference runs before race sessions using EventBridge
  • Built Lambda-based prediction pipeline for race outcome inference
  • Delivered outputs through an interactive dashboard for race insights
SYSTEM 04
Deep Learning / Health ML
ML SYSTEMS

ML & Deep Learning Pipelines

Built multiple ML pipelines across computer vision, audio classification, and health analytics with full preprocessing, training, and evaluation workflows.

PyTorchscikit-learnOpenCVSVMCNNFeature Engineering
  • Built CNN pipelines for spectrogram-based bird call classification
  • Trained SVM models for health outcome prediction using behavioral features
  • Designed reusable preprocessing, feature engineering, and evaluation workflows

// 003 — SELECTED WORK

Projects

TOTAL 7
FEATURED 6
PROJECT 01
AI / NLP
RAG SYSTEM

Football Injury RAG System

RAG pipeline combining GPS tracking, PubMed research, and player history for injury risk prediction. Engineered vector search across 50K+ points with ACWR and PlayerLoad metrics.

P@1 Score
81.5%
MRR
85.9%
Vectors
50K+
PythonQdrantPubMed APIGPS MetricsRAG
PROJECT 02
Prediction / Simulation
MOTORSPORT ML

F1 2026 Race Winner Prediction

Race winner prediction model built for the 2026 Australian Grand Prix using qualifying pace, practice data, driver form, and Monte Carlo race simulation. Fully data driven with zero betting inputs and 2026 regulation aware adjustments for active aero, energy management, and reliability.

Winner
Correct
Russell Win%
59.1%
Simulations
100K
PythonNumPyPandasFastF1Monte CarloReactRecharts
MOTORSPORT ML
PROJECT 03
Full Stack / Security
COMPLETED

Resume Access System

Secure resume sharing workflow with request-based access, time-limited signed URLs, dynamic watermarking, and request tracking. Built with AWS S3, DynamoDB, and Resend to prevent public redistribution and give controlled visibility into resume access.

Storage
AWS S3
Access
Signed URL
Alerts
Resend
Next.jsAWS S3DynamoDBResendSigned URLsWatermarking
COMPLETED
PROJECT 04
Full Stack / 3D
AVIATION TECH

Flight Global — Aviation Intelligence

Live 3D globe showing real time commercial flight positions worldwide. Fleet analytics with airline stats, route density heatmaps, and live delay feeds via OpenSky Network API.

Coverage
Global
Flights
Live
Data
Real-time
Next.jsCesiumJSOpenSky APIThree.jsWebGL
AVIATION TECH
PROJECT 05
Computer Vision / Audio
DEEP LEARNING

Bird Call Classification

CNN models on Mel spectrogram inputs for audio classification. Reduced overfitting with dropout and early stopping. Full pipelines for multi species evaluation.

Binary Acc
88%
Multi-species
57%
Method
CNN
PyTorchOpenCVMel SpectrogramsPython
PROJECT 06
Classification
HEALTH ML

Heart Attack Risk Prediction

Linear, RBF, and polynomial SVM models to predict heart attack risk. Captured nonlinear relationships among sleep, work hours, and BMI using kernel cross validation.

Model
SVM
Eval
ROC AUC
CV
K-Fold
scikit-learnSVMPythonSQLETL

// 004 — BUILT FOR FUN

Boredom Builds

Things built late at night because the idea wouldn't leave me alone.

3D · LIVE DATAIN PROGRESS

Flight Global — Aviation Intelligence

Real-time 3D globe with live commercial flight positions, fleet analytics, route density heatmaps, and delay feeds.

Next.jsCesiumJSOpenSky APIThree.js

// 005 — CAREER LOG

Experience

AUG 2022 — SEP 2022

Data Analyst Intern

Glencore Information and Services Pvt. Ltd.

Data Accuracy
+25%
Business Insights
+15%
Project Efficiency
+20%
Team Scope
Cross-func
RESPONSIBILITIES

Cleaned and transformed large transportation datasets via ETL and Excel

+25% accuracy

Built Tableau dashboards and pivot tables to surface insights across cross-functional teams

BI dashboards

Applied statistical analysis to identify trends, increasing actionable business insights

+15% insights

Queried relational databases with SQL to deliver data-driven recommendations

+20% efficiency

// 006 — ACADEMIC RECORD

Education

🎓

MS, Data Science

Seattle University

Seattle, USA

IN PROGRESS
Jun 2026
🏛️

BE, Computer Science

Sri Venkateswara College of Engineering

Chennai, India

COMPLETED
May 2024

// 007 — BEYOND THE DATA

The Human Side

Because I'm not just a data scientist — I'm a football fan, an F1 nerd, a planespotter, and someone who cries at anime.

MUSIC
The Weeknd

🎵 The Weeknd

Starboy · Blinding Lights · After Hours

Anirudh Ravichander

🎶 Anirudh Ravichander

Hukum · Vikram · Leo · Jailer

FEEL-GOOD FILM
Cars

🏎️ Cars

Disney·Pixar · Lightning McQueen

Baby’s Day Out

👶 Baby’s Day Out

Classic chaos · comfort watch

ANIME
Attack on Titan

⚔️ Attack on Titan

The greatest story ever told.

Your Lie in April

🎹 Your Lie in April

Kousei Arima · Kaori Miyazono

Blue Box

🏸 Blue Box

Taiki Inomata · Chinatsu Kano

Haikyuu!!

🏐 Haikyuu!!

Hinata Shoyo · Volleyball energy

Alya Sometimes Hides Her Feelings in Russian

❄️ Alya Sometimes Hides Her Feelings in Russian

Masachika Kuze · Alya

K-DRAMA
Our Beloved Summer

🍂 Our Beloved Summer

Choi Ung · Kook Yeon-su

Melodrama

🎭 Melodrama

Joo Sung-hee · Ryu Han-joon

C-DRAMA
Shine On Me

Shine On Me

A quiet love story that lingers.

Put Your Head on My Shoulder

💙 Put Your Head on My Shoulder

Situ Mo · Gu Weiyi

// 008 — TRANSMISSION

Let's Talk

Open to full-time roles, internships, and research collaborations in data science & ML.

📍 Seattle, USA  ·  📞 (206) 801-4382

LinkedInGitHub