Walker Hyman
Applied AI Software Engineer & Data Scientist

Walker Hyman

Data Science & AI at William & Mary - Philosophy Minor. Passionate about building impactful AI products.

Scroll
About

Who I am

I'm a senior at William & Mary studying Data Science (AI concentration) with a Philosophy minor.

I've built multi-agent systems and RAG workflows in production, trained deep learning models from scratch, and shipped full-stack AI products end to end.

Walker Hyman
Experience

Professional Experience

Babel Street

Applied AI Engineering Intern

May — Aug 2025
  • Architected a production multi-agent system coordinating deep research—cut report generation from hours to under minutes.
  • Reduced irrelevant RAG results by 60% with a semantic-keyword hybrid retrieval pipeline.
  • Built tracing and observability infrastructure (prompt management, eval pipelines, user-level metrics) to accelerate iteration across agent workflows.
PythonMulti-Agent SystemsRAGLangfusePydanticPydanticAI

Centra Logistics

Software Engineer

Feb 2023 — Aug 2024
  • Built a novel unified AI commercial real estate property management and forecasting system.
  • Created CRE project management tooling to track costs, status, and progress across active projects.
  • Built portfolio dashboards for analytics.
  • Shipped forecasting tools for revenue projections and market analysis.
Full-StackPostgreSQLPythonJavaScriptAWSDjango
Selected Projects

What I've built

Full-stack AI products, graph neural networks for bot detection, generative models, and NLP.

03

Twitter Bot Detection via Graph Transformers

Multi-modal bot classifier on TwiBot-22 (1M users, 340M edges) fusing heterogeneous graph transformers, LoRA-fine-tuned XLM-RoBERTa text embeddings, and 23 engineered behavioral features. ~90% accuracy.

PyTorchPyGHuggingFacePEFT/LoRASLURM
04

VAE Face Generation on CelebA

Standard VAE and VQ-VAE for face image generation and reconstruction on 200K+ CelebA images. VQ-VAE uses a learned codebook with convolutional encoder/decoder. Evaluated with FID, PSNR, and MSE.

PyTorchTorchvisionpytorch-fidSLURM
05

LSTM Code Summarization

End-to-end pipeline for Java method summarization: mines ~50K method/Javadoc pairs from GitHub, tokenizes with CodeT5+, and trains a seq2seq LSTM with attention. Evaluated on BLEU-1.

PyTorchHuggingFaceCodeT5+GitHub API
06

Qwen RAG for Java Bug Fixing

End-to-end pipeline: trains a SentencePiece tokenizer on CodeSearchNet, pre-trains T5-small with span corruption, fine-tunes on bug fixing, and benchmarks against Qwen2.5-Coder zero-shot and CodeBERT-retrieval RAG.

PyTorchHuggingFaceT5QwenCodeBERTSentencePieceSLURM
Expertise

Technologies & skills I work with

ML & AI
PyTorchHugging Facescikit-learnTensorFlowPydanticPydantic AIW&B
Full Stack
PythonTypeScriptReactDjangoFastAPINode.jsPostgreSQLSQLTailwind
Infrastructure
DockerKubernetesAWSSLURMGitLinux
Research
NLPDeep Learning ArchitecturesGenerative ModelsMulti-Agent SystemsRAG
Contact