Hi, I'm Peyton.
Talk nerdy to me.

AI Developer & Database Engineer
From designing cyber security databases to building LLM-powered platforms, my focus is on creating systems that think as clearly as they scale. You could say I query the future.

I built a mini-me

Say hello to Peyton.ai—my LLM-powered resume chatbot experiment. It started off as an implementation of a tiny MoE model trained from scratch, now it's RAG attached to the dataset to accurately answer questions about my work experience. Hosted on my locally distributed GPU cluster.

Featured projects

Griffin

Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.
Paper implementation

RNN Attention Hybrid

Confidence Transformer

Transformer model that reports confidence in its predictions.

Transformer Confidence Estimation

F5 TTS

Fast and efficient Text-to-Speech model.

TTS Speech Synthesis

LLM Memory Modules

Exploring memory mechanisms for Large Language Models at scale.

LLM Memory Scaling

Simple ViT

A straightforward implementation of the Vision Transformer.

Vision Transformer Computer Vision

Simple CLIP

A straightforward implementation of CLIP.

CLIP Multimodal

Tiny MoE

A small Mixture of Experts language model.

MoE LLM

Conversational Transformer

Transformer model focused on conversational AI.

Transformer Chatbot

Action Transformer

Transformer model for predicting sequences of actions.

Transformer Reinforcement Learning

YOLOv5 DeepQ Learning Model

Combining YOLOv5 object detection with Deep Q-Learning.

Object Detection Reinforcement Learning

Single Architecture Ensemble

Multi Input-Multi Output Transformer models with early exit
Paper implementation

Ensemble Methods Deep Learning

T5 SpeechtoSpeech

Speech-to-speech translation model based on T5.

T5 Speech Translation

Skills and expertise

Database technologies

PostgreSQL MongoDB MySQL Supabase

AI and Machine Learning

PyTorch Transformers LLMs Agents

Programming languages

Python VB.NET Golang JavaScript Lua Bash some Java, C#, C/C++

Cloud and infrastructure

AWS GCP Azure Docker Kubernetes Terraform

About me

I used to just build databases. Now, I train the AI that speaks from them. Code, data, and curiosity—that's my stack.

I started off as a nuclear machinist's mate for the Navy, now I'm a developer and database engineer with 5+ years who builds intelligent systems with structured data and large language models. Whether it's designing resilient databases, fine-tuning LLMs, or developing unique AI systems, I bring structure and intelligence together to create tools that think, respond, and evolve. Let's make machines a little smarter and a lot more useful.

© Peyton Tolbert 2025 | Github | LinkedIn | X.com