Seeking Summer 2027 internships

Kyler Zook

Machine Learning & Computational Biology

Undergraduate Researcher · University of Missouri — Columbia

01 About

Machine learning, meet genomics.

I am a junior at the University of Missouri — Columbia pursuing a B.S. and an accelerated M.S. in Computer Science, with minors in Mathematics and Biological Sciences. What pulls me toward this intersection is how directly these methods are changing the way we understand disease and design treatment.

In Dr. Jianlin Cheng's lab I develop methods for gene regulatory network inference — building the multi-source pipelines, quality-control tooling, and evaluation infrastructure that graph neural network models are trained and measured on. I am co-first author on a NeurIPS 2026 submission under review.

Outside the lab I build systems: distributed job platforms, GPU kernels, and retrieval pipelines. I care about the unglamorous layer — reproducibility, data integrity, and benchmarks you can actually trust.

Languages

  • Python
  • C/C++
  • Java
  • SQL
  • JavaScript
  • Bash

Libraries & Frameworks

  • PyTorch
  • TensorFlow
  • Scikit-learn
  • Pandas
  • NumPy
  • SciPy
  • LangChain
  • FastAPI

Infrastructure

  • Docker
  • PostgreSQL
  • Redis
  • MongoDB
  • AWS
  • Git
  • Linux

Focus Areas

  • Gene Regulatory Networks
  • Graph Neural Networks
  • Single-cell Genomics
  • Multi-omics

02 Selected Work

Systems built end to end.

01

GRN-Bench — Distributed Benchmark Platform

Self-hosted service running multi-seed graph ML experiments as queued jobs. Idempotent writes survive 500 duplicate submissions and forced worker kills.

0p95, from 1.2 s
0metric rows
47→12GB deduplicated
0sweep, from 14 h
  • Python
  • FastAPI
  • PostgreSQL
  • Redis
  • Celery
  • Docker
View project

02

Custom Triton Kernels for GNN Operations

Hand-written GPU kernels for the sparse message-passing primitives at the core of graph neural networks, cutting the memory traffic and launch overhead that dominate training.

fused kernel neighbours aggregate
  • Triton
  • PyTorch
  • CUDA
View project

03

Creator Knowledge Base & RAG Platform

End-to-end pipeline ingesting YouTube captions, metadata, and transcripts into per-creator knowledge bases, with similarity search across 4,000 videos per creator.

4,000 videos per creator transcriptchunk embedvector DB similarity search → grounded answer
  • Python
  • LangChain
  • Ollama
  • AWS
View project

04

Redis-Inspired Multithreaded Key-Value Store

In-memory key-value store built from the socket up. Custom memory management and a hand-rolled TCP layer serve real-time SET/GET under stress testing.

SET / GET clientTCP parserhash table custom memory pool · serialization
  • C++
  • TCP Sockets
  • Multithreading
View project

03 Research & Experience

Where the work happens.

Machine Learning Research — Gene Regulatory Network Inference

Aug 2025 – Present Dr. Jianlin Cheng's Lab · University of Missouri — Columbia
  • Architected a multi-source pipeline ingesting, normalizing, and version-controlling genomic datasets from six public repositories into a unified schema spanning 200+ cell types across human and mouse references.
  • Wrote automated QC tooling that benchmarks generated networks against reference standards and gates builds on objective acceptance criteria before training.
  • Built the evaluation harness for GNN link prediction: fixed splits, controlled negative sampling, multi-seed AUROC/AUPRC reporting.
  • Owned the literature-validation agent and multi-omic validation component for a NeurIPS 2026 submission.

AI Engineer (Contract)

Jan 2024 – May 2025 Virtuverse AI · Remote
  • Architected and deployed an end-to-end YouTube ingestion pipeline via the Google API and custom scraping, automating knowledge base creation for creator-specific chatbots.
  • Designed the preprocessing, chunking, and embedding workflow backing a RAG pipeline, improving retrieval relevance and grounding.
  • Integrated a vector database with similarity search across 4,000 videos per creator, deployed on AWS EC2.

04 Publications

Peer-reviewed work.

Under Review

A. Hedge, K. Zook, R. Kim, J. Cheng. “Agent-Based Gene Regulatory Network Inference.” NeurIPS, 2026.

Co-first author. Developed the automated literature-validation agent and the multi-omic validation component integrating chromatin accessibility and transcriptomic data.

In Preparation

K. Zook, J. Cheng. “A Benchmark for Evaluating Graph-Based Gene Regulatory Network Inference.”

First author. Target submission December 2026, with a public dataset release and reproducible evaluation protocols.

05 Education

University of Missouri — Columbia

GPA 3.84 · High Dean's List, all semesters · Mark Twain Scholarship

B.S., Computer Science

Aug 2024 – May 2028

  • Advanced Algorithm Design
  • Object-Oriented Programming
  • Mathematical Statistics
  • Unix/Linux Systems

Accelerated M.S., Computer Science

In progress

  • Concentrated in machine learning and algorithms

Minors

Mathematics & Biological Sciences

  • Discrete Mathematics
  • Introduction to Mathematical Statistics
  • Coursework supporting computational work on transcriptional regulation
Kyler Zook · Columbia, Missouri