Portfolio / 2026

Software Engineer

Charlottesville, Virginia

Icarus flying over a geometric Aegean city

Plate 01 / Ambition needs systems

Engineer · Researcher · Builder

Brett Haas

I build intelligent systems that hold up in the real world.

Full-stack software engineer building reliable, intelligent products across web, mobile, and AI systems.

Explore selected work
616K+COCO captions filteredUniversity of Virginia
28.9%RMS next-token bias reductionUniversity of Virginia
55%load-time improvementRefraction Innovation Hub
99.5%crash-free sessionsRefraction Innovation Hub

01 / Craft

The craft behind the flight.

My work sits where software engineering, machine learning, and product judgment meet.

I like difficult systems with visible stakes: steering model behavior, testing frontier agents, and shipping cross-platform products whose performance can be measured—not merely described.

A cliffside workshop with sculptural wings

Research systems

Production engineering

Human-centered interfaces

02 / Flight log

Trajectory

From research and evaluation to production mobile systems: a path shaped by rigor, iteration, and useful outcomes.

A rising coastal city and lighthouse at dusk

01

University of Virginia

ML Research Assistant

Inference-time activation-steering research focused on language-model visual bias.

Nov 2025 – May 2026Charlottesville, VA

02

Scale AI

GenAI Technical Advisor Intern · SEAL

Frontier-model safety, evaluation, and agent reliability work on the Scale AI SEAL team.

Jun 2025 – Dec 2025Remote, USA

03

Refraction Innovation Hub

Software Engineer Intern

Cross-platform nutrition and food-recognition product development across mobile, AI, and cloud systems.

Jun 2025 – Aug 2025McLean, VA

04

University of Virginia

B.S. in Computer Science

Systems, cybersecurity, software engineering, and machine-learning research.

May 2026GPA 3.7

03 / Field studies

Selected work

Three builds across computer vision, product interface, and language-model research. Each chapter is presented in full—no hidden cards or modal detours.

Case 01

Computer Vision · Python · Analytics · Sports Tech

Court Vision

Computer vision basketball analytics platform for shot tracking and player movement insights.

A geometric arena with analytical trajectory arcs

Brief

Turn basketball footage into practical, coach-friendly signals for reviewing shots, movement, and possession.

Approach

Extract event-level patterns from video, then organize the results in a focused visualization layer for fast game review.

Technical focus

Computer-vision analysis, event pipelines, movement trends, and readable sports analytics.

Repository

Case 02

React · Audio · Streaming · UI/UX

Beat Stream

Music streaming and discovery experience focused on smooth playback, curation, and social sharing.

Coastal architecture crossed by rhythmic signal ribbons

Brief

Make music discovery, playback, curation, and playlist sharing feel immediate in a modern web experience.

Approach

Reduce the distance between search and listening with quick interaction loops and a clear information hierarchy.

Technical focus

React interface architecture, audio playback, discovery flows, and responsive product design.

Repository

Case 03

Python · PyTorch · NNSight · LLM Evaluation

Vision Bias Steering

LLM steering experiments for shifting model outputs between spatial and descriptive language.

A labyrinth observatory with two controlled light paths

Brief

Study whether inference-time steering can shift captions between spatial and descriptive language without retraining model weights.

Approach

Train and validate steering vectors, run local and multi-model sweeps, then compare language behavior through evaluation and plotting utilities.

Technical focus

PyTorch experimentation, NNSight interventions, reproducible sweeps, and language-model evaluation.

Repository
Distant wings crossing a calm sunrise horizon

04 / Next horizon

Keep building.

I’m interested in ambitious engineering teams working across intelligent systems, reliable products, and applied research.

Email Brett