Skip to content
View rasiulyte's full-sized avatar
3 followers · 1 following

Block or report rasiulyte

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rasiulyte/README.md

Hi, I'm Rasa Rasiulyte 👋

AI Quality & Evaluation Strategist | Building expertise in AI system reliability, safety, and trustworthiness

🎯 What I'm Doing

I'm on a systematic journey to deepen my expertise in AI quality and evaluation, combining:

  • 12 years at Microsoft (Test → SDET → SDE)
  • MS in Computer Science from Johns Hopkins University (2023)
  • Outlier (Scale AI) — Expert evaluator for programming projects, ensuring high-quality outputs across C++, C#, Python, Java, and SQL
  • Hands-on AI tool evaluation — documenting what works, what breaks, and why it matters

🔬 Current Focus

Systematically evaluating AI development tools through a quality engineering lens:

  • Assessing AI coding assistants for reliability, safety, and real-world performance
  • Documenting edge cases, failure modes, and unexpected behaviors
  • Building reusable evaluation frameworks for AI-assisted development

📊 What I'm Building Here

This GitHub tracks my AI evaluation work:

  • /ai-tool-evaluations — Structured assessments of AI tools
  • /edge-cases — Documented failures and interesting behaviors
  • /evaluation-frameworks — Reusable testing approaches

🔗 Connect

Popular repositories Loading

  1. rasiulyte rasiulyte Public

    AI Quality & Evaluation | Ex-Microsoft | MS CS Johns Hopkins

  2. ai-tool-evaluations ai-tool-evaluations Public

    Structured evaluations of AI development tools from a quality engineering perspective