SHREYANSH KUMAR

AI/ML Engineer with 2.5+ years of expertise in machine learning, deep learning, and data analytics. Skilled in building scalable models, data pipelines, and cloud-based deployments.

DOWNLOAD PDF  ↓
LAS VEGAS, NV (617) 259-0101 LINKEDIN ↗ GITHUB ↗
01 — EXPERIENCE
01 02/2026 — PRESENT

AI/ML Engineer

Droisys — Las Vegas, NV

Hardened observability across a multi-module Spring Boot codebase with SLF4J structured logging. Contributed to the Table Guard Web API exposing JWT-secured REST resources for casino surveillance. Supported ETL + rule-engine pipelines ingesting and transforming table game data for real-time risk signals.

Spring Boot SLF4J REST APIs PostgreSQL ETL JWT
02 03/2025 — 02/2026

Lead Data Analyst

Chicago Education Advocacy Cooperative — Remote

Designed an AI-powered multi-agent tutoring platform that improved learner outcomes by 30% and lifted engagement by 35%. Architected a scalable RAG pipeline with recursive chunking and metadata-aware vector search, cutting topic confusion by 42%. Built intelligent document processing with 98% extraction accuracy and 90% reduction in API costs.

LLMs RAG Multi-Agent LangChain CrewAI OCR Computer Vision
03 08/2022 — 06/2023

Data Scientist

Nexdigm — Gurugram, India

Led development of a Python-based time series forecasting tool using ARIMA, SARIMA, SARIMAX, VARMAX, and RNN models, reducing exploratory time by 70%. Automated hyperparameter tuning across 50+ iterations per dataset, cutting delivery from 3 weeks to 4 days. Enhanced model accuracy by 12% with iterative feature engineering.

Time Series ARIMA RNN Python Feature Engineering Automation
04 02/2022 — 06/2022

Data Analyst Intern

TransOrg Analytics — Gurugram, India

Predicted sales using ARIMA and Prophet models, reducing overstock by 12% and stockouts by 9%. Improved product discovery with semantic embedding search, boosting session duration by 30%. Developed K-Means/DBSCAN customer segments for personalized campaigns that raised repeat purchase rates by 18%.

Prophet Semantic Search K-Means DBSCAN Embeddings
02 — PROJECTS
01

Big Data Dining Recommendation System

Large-scale retrieval-augmented recommendation engine over the 8GB+ Yelp dataset. Semantic retrieval paired with LLM-based generation delivers context-aware dining suggestions across 10K+ businesses with low-latency querying.

RAG LangChain BigQuery Vector DBs NLP Semantic Search
95% Response Accuracy
8GB+ Dataset Size
02

Health Risk Classification Pipeline

End-to-end ML classification pipeline with advanced feature engineering and hyperparameter tuning. SMOTE for class imbalance and Boruta for feature selection raised predictive performance by ~18%. Dimensionality reduction cut training time by ~30% without accuracy loss.

Scikit-learn SMOTE Boruta Lasso Feature Engineering
~18% Performance Gain
~30% Faster Training
03 — SKILLS

ML & AI SYSTEMS

RAGLLMsNLPComputer Vision ClassificationRegressionClusteringGradient Boosting Time SeriesA/B Testing

FRAMEWORKS & LIBRARIES

PyTorchTensorFlowScikit-learnKeras XGBoostHugging FaceLangChainCrewAI

CLOUD & DATA

GCPAWSAzureApache Spark BigQueryWeaviateChromaPostgreSQL Streamlit

LANGUAGES

PythonSQLC++R
04 — CERTIFICATIONS
MICROSOFT AZ-900 Azure Fundamentals
MICROSOFT AI-900 Azure AI Fundamentals
ORACLE Cloud Infrastructure Foundations & Cloud Operations Associate
IBM Data Science & Machine Learning Professional
05 — CONTACT

LET'S BUILD
SOMETHING
TOGETHER.