me@elucia.fyi:~$

        Hi! I'm Ilya "Elucia" Khruschev, a Full Stack Data Scientist, Data Engineer, and ML Engineer with eight years of experience designing and building end-to-end data and machine learning pipelines. I collaborate closely with internal leadership and C-suite client executives at organizations including Snowflake, SpaceX, Cardinal, IBM, and CTA-CES. Based in Arlington, VA, I specialize in architecting solutions that span from raw data ingestion through model deployment and visualization.

        My work encompasses everything across the data lifecycle: developing geo-location streaming architectures for time-sensitive tracking, designing experiments to measure AdTech metrics, and creating real-time data analytics and automated news-reading services for Fortune 500 companies. I build and mentor BI and Data Science teams, leading forecasting and Bayesian analysis initiatives, driving experimental design, and integrating LLM tooling for scalable insights. Whether it's crafting ETL pipelines, training predictive models, or deploying dashboards for cross-functional stakeholders, I ensure each stage delivers measurable impact and drives data-informed decision-making.

        I'm based in Arlington, VA.

Ilya "Elucia" Khruschev

Email: me@elucia.fyi
Phone: 610.850.2627
Location: Arlington, VA

Professional Summary

Data Scientist and Engineer with expertise in experimental design, machine learning, applied statistics, team building, and analytics, who brings insatiable curiosity, ideas, and solutions. Eight years designing and building experiments and end-to-end data and ML pipelines, and collaborating with internal leadership and C-suite client executives at Snowflake, SpaceX, Cardinal, IBM, CTA-CES, Department of Homeland Security, and Department of Defense.

Technical Skills

Programming Languages:
Python
SQL
NoSQL
Big Data & Analytics:
BigQuery
Spark
Presto
Trino
Visualization & BI:
Tableau
ElasticSearch
DevOps & Infrastructure:
Airflow
Docker
Git
Pentaho
Jenkins
Cloud Platforms:
GCP
AWS
Azure DevOps
Operating Systems:
Mac OS
Linux (Various distributions)
LLM/Tools:
RAG
MCP
API integration
Vector databases
Agent frameworks
n8n
Stats & Modeling:
Forecasting
Experimental Design
ML Models
Causal Inference
Bayesian Inference
Statistical Modeling

Experience

Senior Data Scientist / ML Engineer
AdTalem, Chicago, IL (Remote) 2023 – Present

  • Developed and implemented enrollment forecasting models, reducing total marketing budgets by 18%
  • Deployed a student payment propensity model, leading to a projected $7.2M yearly return in account repayments
  • Manage team of data scientists and junior data scientists

Senior Data Scientist | Product Analytics
NextRoll, San Francisco, CA (Remote) 2021 – 2022

  • Directed multiple cross-platform projects between Engineering, Customer Success, Marketing, Finance, etc.
  • Designed A/B tests evaluating new product features driving customer engagement and reducing customer churn
  • Built data pipelines for and evaluated bounce rates, conversion rates, and other KPIs for customers
  • Served as customer facing lead for our largest customer, applying a strategy to evaluate their AdTech business

Data Scientist | Engineer
Expression Networks, Washington, DC 2020 - 2021

  • Designed and built ETLs to create centralized database for military Electromagnetic Frequency Spectrum data
  • Built big data streaming pipeline processing 2M+ geo coordinates/day and meta data for mission critical decisions
  • Developed easy-to-use ML healthcare models for real-time battlefield analysis and private sector hospital use

ML Engineer
Attain, McLean, VA 2020

  • Recruited to design and develop ML pipelines and models, reporting to the software engineering principal
  • Built DevSecOps AI / ML pipelines in big data systems for USCIS at DHS, under a secret-level security clearance

Data Scientist
PublicRelay, Tysons Corner, VA 2018 - 2019

  • Prototyped and visualized models for binary classification and time series analysis for Fortune 500 clients
  • Designed and coded multi-class multi-label classification models to automate sorting and article labeling
  • Created AI / ML solutions using SVMs and Deep Neural Networks for media analysts and end-users
  • Researched NLU application for chatbots to provide real time customer assistant to clients/analysts

Business Intelligence Analyst
PublicRelay, Tysons Corner, VA 2017 - 2018

Business Analyst
PublicRelay, Tysons Corner, VA 2015 - 2017

Media Analyst | Account Manager
PublicRelay, Tysons Corner, VA 2013 - 2015

Education

MS Candidate - Statistics
The George Washington University | 2016 - 2017

BBA Degree - Finance/Statistics
The George Washington University - School of Business | 2013

Download Full Resume

Download Resume (PDF)

MCP News Server

A cutting-edge Model Context Protocol (MCP) server that delivers aggregated, unbiased news from multiple sources. Built to combat information silos and media bias, this intelligent news aggregation system provides balanced perspectives on current events, perfect for AI assistants and data-driven decision making.

View on GitHub

SQL-in-Python Syntax Highlighter

An elegant VS Code extension that brings sophisticated SQL syntax highlighting to embedded SQL strings within Python files and Jupyter notebooks. Features intelligent detection of SQL patterns, multi-line query support, and seamless integration with existing Python workflows for data scientists and analysts.

View on GitHub

Elucia's Developer Dotfiles

A carefully curated collection of configuration files, shell scripts, and productivity tools that power my development environment. Features optimized terminal setups, custom aliases, Git configurations, and workflow automation scripts refined through years of data science and engineering work.

View on GitHub

Food Tracking App

A versatile calorie tracking application, deployable locally or in the cloud, that leverages LLM-powered food recognition to analyze an image of a plate or label and return detailed macro and calorie information. It maintains a comprehensive log of all foods consumed and provides intuitive charts visualizing calorie intake over time.

View on GitHub

Get In Touch

I'm always excited to discuss new opportunities, collaborations, or simply chat about data science and machine learning. Feel free to reach out!

Location

Arlington, VA