data engineer · data scientist · bellevue, wa

I turn messy
data into
clear signal.

MS Quantitative Biomedical Sciences · Dartmouth
BS Computer Science · University of Maryland
Building production ML systems, Bayesian models,
and pipelines that actually ship.

~/ayush

proficiency index

Python / ML
95%
SQL / DBs
90%
React / TS
80%
Bayesian stats
82%
AWS infra
75%
Causal inf.
70%
3+
yrs production eng
7+
roles held
4+
shipped platforms
questions asked
01selected work

data platform · agri-tech

QA/QC Ecosys Platform

Production quality assurance system for field-level carbon data. React/TypeScript frontend, FastAPI backend, batch deletion pipelines across subfield hierarchies with AWS S3.

FastAPIReactTypeScriptAWS S3SQLAlchemy

health data science · modeling

Malaria Transmission Model

Bayesian inference on malaria intervention efficacy for global health policy evaluation. Quantitative modeling designed for decision-making at scale.

PythonStanBayesianEpi modeling

ml · explainability

Modular ML Pipeline

Automated feature selection, cross-validation, and SHAP-based explainability. Generalizes across health and financial datasets with MLflow tracking.

Scikit-learnSHAPMLflowpandas

data engineering · infra

AWS Pipeline Automation

SNS/Chatbot alert system with S3 geospatial data management for large-scale agricultural pipelines. Reduced failure response time by 60%.

AWS SNSLambdaS3Python
02skill distribution

hours by domain (est. 3yr)

domain coverage

03experience

Oct 2022 – present

HabiTerre

Data Engineer

HabiTerre · Bellevue, WA

Building QA/QC platform for carbon data pipelines. React/FastAPI full-stack, AWS S3/SNS infra, geospatial batch processing, DAO patterns at subfield granularity.

Jun 2022 – Aug 2022

TCG

Data Science Intern

TCG Digital

Customer review text analytics for sentiment and emotion classification. Topic modelling on free-flow text (aspect extraction) and aspect-based sentiment analysis using transformer models.

Apr 2022 – Jun 2022

Swiss Re

Data Science Student Consultant

Swiss Re · Hanover, NH

Project sponsored by Swiss Re and Insured Connect for Dartmouth's Data Analytics Project Lab. Developed a mathematical model to identify underinsured policyholders and quantify adequate coverage.

Mar 2022 – Jun 2022

Dartmouth College

Machine Learning Teaching Assistant

Dartmouth College · Hanover, NH

Graduate TA for COSC274: Machine Learning and Statistical Data Analysis, taught by Prof. Soroush Vosoughi.

Jun 2019 – Aug 2019

FZ

DevOps / BigData Intern

flydubai · Dubai, UAE

Built statistical models for airline competitor analysis. Data ingestion with Cloudera/Apache Kafka. CI/CD pipelines with Azure, Git/Jenkins integration.

04education
Dartmouth College
Dartmouth College
Hanover, NH · 2021 – 2022
MS · Quantitative Biomedical Sciences
Health Data Science track — Bayesian modeling, causal inference, clinical data pipelines, epidemiological methods.
Bayesian statscausal inferenceRPythonStan
University of Maryland
University of Maryland
College Park, MD · 2017 – 2021
BS · Computer Science
Algorithms, systems programming, probabilistic inference, data structures, linear algebra, statistical theory.
algorithmsstatisticsJavaCprobability