Sidharth Swamy

I love software, math, and data

Accelerated BS/MS Applied Math & Stats, CS Minor — Stony Brook University

Download Resume

Experience

Data Science Intern

Zeno  EV Startup

Apr 2025 – Sep 2025

  • Built a data pipeline for Modbus and monitoring devices at battery swap stations (India, Africa), ingesting via NNG sockets and streaming over UDP/TCP with zlib compression into Parquet files on AWS S3.
  • Designed an ingestion system for CAN logs over UDP into MF4 files, supporting reliability and predictive maintenance analysis.
  • Built an interactive analytics layer (DuckDB + Voila) to detect outages and forecast station-level performance, providing inputs for operations research models in fleet reliability, capacity planning, and energy optimization.
  • Produced Windows firmware-flashing binaries and debugged GitHub Actions builds, resolving false malware detections.

Projects

Lithium-ion Battery Cycle Life Prediction

A linear backbone with a Gaussian Process fit to its residuals, beating the Severson et al. (Nature Energy, 2019) Elastic Net with 17% smaller errors on average on out-of-distribution batches

Python scikit-learn

MNIST Convolutional Neural Network

CNN built from scratch in Python that classifies handwritten digits from the MNIST dataset.

Python NumPy Deep Learning

Boeing Database

SQL database integrating 45,000+ data points on Boeing aircraft, airports, airlines, flights, and incidents.

SQL MS Access Database Design

Airfleets Scraper

Python web scraper for airfleets.net that extracts production list data from selected aircraft types.

Python BeautifulSoup Web Scraping

Gmail Filter

Python tool utilizing the Google Gmail API to filter and delete emails based on custom keywords and senders.

Python Google API

Reports

One Predictor Regression Analysis

Multivariate imputation of missing data by chained equations.

R Regression Statistics

Multiple Regression Computing Project

Multiple regression + Lasso modeling of gene-environment interactions.

R Lasso Statistics

Skills

Python Python
R R
Java Java
MS Access MS Access
scikit-learn scikit-learn

Coursework

Software

Computational Geometry
  • Convex hulls, triangulation, Voronoi diagrams, visibility, robot motion planning
  • Algorithms for graphics, robotics, GIS, and optimization
Principles of Programming Languages
  • Functional and logic paradigms; type systems; scoping and binding
  • Parsing, semantic analysis, and code generation
Data Structures & Algorithms
  • Sophisticated OOP; data types and structures
  • Algorithm design for time and memory efficiency
Object Oriented Programming
  • Java: encapsulation, inheritance, polymorphism
  • Software debugging and testing techniques

Math

Analysis of Algorithms
  • Searching, sorting, FFT, graph algorithms; complexity analysis
  • NP-completeness and lower-bound analysis
Operations Research: Deterministic Models
  • Linear programming: simplex method, primal-dual theory
  • Applications in economics, transportation, and production
Probability & Statistics
  • Distributions, confidence intervals, significance tests, regression in R
Graph Theory
  • Proof-based reasoning; combinatorial methods
  • Network algorithms, optimization, game theory

Data

Statistical Learning (Grad)
  • Regression, SVM, Random Forests, GAMs, Neural Networks, Transformers
  • Bootstrapping, regularization, PCA, clustering in R and Python
Data Management (Grad)
  • Database architecture, querying, transactions, distributed systems
  • Warehousing, cleaning, mining; graph and vector databases
Data Analysis
  • Regression, ANOVA, chi-square, F-distributions
  • Projects in R and Python on linear and multiple regression
Data Science & Machine Learning
  • Machine learning and GIS mapping applied to economics
  • Neural network implementation in teams