R Javair Ratliff
Codex
ratliff.nyc
Discipline
Software & AI
Location
New York
Anno
MMXXVI
Independent Software & AI Engineering

I build the parts of software that don't have a Stack Overflow answer.

Javair Ratliff — an independent software and AI engineer in New York. Nine years spent carrying hard technical work, from language-model internals to computer vision, out of the research notebook and into dependable production.

Ideas from the lab, drawn until they hold under load.

φ 1 : 1.618… SECTIO AUREA
Fig. — sectio aurea · the golden section
IX+
Years in production
600+
GitHub stars, open source
1,000s
Daily users served
fol. ii — practice

Engineering across the full stack of modern AI.

i.

AI & Language Models

Representation engineering, model-behavior modification, and inference pipelines — taking a method from a paper to a system you can actually deploy. Creator of the abliteration technique.

ii.

Full-Stack & Cloud

Serverless architectures, APIs, and backends on AWS — built to scale cleanly from prototype to thousands of daily users without a rewrite waiting on the other side.

iii.

Computer Vision & ML Systems

Real-time, GPU-accelerated vision and pose-detection systems, plus the unglamorous deployment plumbing that keeps models running reliably in the wild.

iv.

Prototyping & Technical Advisory

Credible prototypes for hard technical bets, and the architecture review that tells you — honestly — whether an idea survives contact with scale.

fol. iii — selected work

A few things I've built.

I

Abliteration

An open-source representation-engineering technique for steering large language model behavior through direct weight editing — no fine-tuning required. Adopted widely across the open-source AI community.

2024
PyTorchRepr. Engineering600+ ★
II

Real-Time Vision Exhibit

3D ball-trajectory and speed tracking for an interactive exhibit at a New York museum, built on custom GPU-optimized algorithms and seen by thousands of visitors every day.

Museum
Computer VisionCUDAReal-time
III

Serverless Health Platform

An AWS Lambda and DynamoDB screening platform that scaled to thousands of daily users during COVID-19 reopening, driven by automated SMS compliance workflows.

2020
AWS LambdaDynamoDBREST
fol. iv — profile

Nine years from idea to production.

I've spent nine-plus years building production systems — from GPU-optimized inference pipelines to serverless platforms serving thousands of people a day. My work sits where machine-learning infrastructure, language-model internals, computer vision, and distributed systems overlap.

I'm at my best with teams who have a genuinely hard problem and need someone who can move between research and shipping without dropping either. Self-taught, practicing since 2008, based in New York and working with teams anywhere.

fol. v — get in touch

Have something hard to build?