Unreal DevOps Engineer
Nov 2024 - Jan 2026
Working on Avatar Client, AI model integration, pixel streaming, networking systems, devops + automation, UI, audio processing, and bugfixing. </br> Helped lead company toward acquisition by Luma AI.
Project Overview
from official website
We've created a new generation of video agents — expressive, emotionally aware, and skillful at navigating complex conversations. Whether coaching, interviewing, or supporting someone through a tough moment — they're capable, memorable, and remarkably human.
Demos
Resume Highlights
• Created processes for deploying Naughty Dog quality visuals on Linux AWS instances that were streamed to users at stable 1080p 30fps. 99.9% success rate, with ability to gather traces and logs on deployed hardware.
• Ensured high quality, low-latency video stream from Unreal while working in inconsistent network conditions.
• Owned deployment process to production and ensured stability for consistent weekly investor demos.
• Developed artist pipeline for ensuring and correcting visual parity between Windows and Linux. Built automated build, cook, and deployment pipelines for Windows, Mac, and Linux, reducing manual release overhead.
• Diagnosed LLM state machine failures that users encountered and resolved prompt alignment issues.
• Implemented Unreal to LLM behaviors, presentation mode, and conversation-state fixes for agent interactions
Job Overview
One of the three Unreal engineers working on the project. Working with veteran talent, including ex Sony VFX and Character Artists and animators and working directly under the cofounder of Naughty Dog ~ Andy Gavin. Our small team focused on the visual "puppet" side of the AI. I joined and soon developed/owned our entire build, deployment, and validation pipeline with QA. Diagnosed issues in packaging as they arose. Created animator tooling and overhauled tooling UI to be procedural throughout our expanding featureset.
We then quickly pivoted quickly into pixel streaming to target mobile deployment, hosting our builds on AWS EC2 GPU Linux servers. I led the charge on deployment procedures and automation for this new system, including gathering traces and logs on target hardware to ensure a consistant 30fps on a reasonable GPU.
Found a bug in these traces at one point that made our cpu tick time 50x faster and let us hit our cpu targets easily. Consistantly tested for reproducable hitches and diagnosed to ensure stable framerate.
Soon expanded into behavior programming, acting as one of the few full stack engineers across backend and frontend, designing our presentation system's behavior and unreal implementation with Chromium to support more flexiblity with our web deployment team.
It's a startup, so generalist mindset and adaptability are huge. I was always eagar to throw my hat in the ring and try something new.
Developed automation tooling, scaling for multi-platform release cycles on win/linux. Handled all unreal side logic for deploying to pixel streaming, resolving linux conflicts. I started expanding the work I was doing and moving into the cognitive behavioral, AI prompting side of the system.