Skip to content
View TatsianaMark's full-sized avatar

Block or report TatsianaMark

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
TatsianaMark/README.md

AI Governance, Red Teaming & Responsible AI Systems

I build, test, and audit AI systems that are safe, fair, and production-ready. My work sits at the intersection of AI safety, fairness engineering, and regulatory compliance. I turn the gap between "AI principles" and "production reality" into structured, actionable practice. I bring a quality engineering foundation to this: systematic testing, regression thinking, and production reliability applied to the harder problem of AI system behaviour.

Open source

I created and maintain the Fairness Assessment, Action & Implementation Playbook series. Practitioner-first frameworks for evaluating, correcting, and delivering AI systems in real product environments. Built openly for teams who need to move from principles to production-ready checks.

Red teaming & adversarial testing

I conduct structured red teaming exercises: adversarial input testing, edge case probing, failure mode mapping, and model behaviour stress-testing. Built to surface risks before they reach users.

AI accountability stack

• Audit & Testing: bias detection, distribution shift, explainability, drift monitoring

• Regulatory Alignment: EU AI Act · GDPR Art. 22 · NIST AI Risk Management Framework · ISO/IEC 42001 · ICO · HIPAA

• Team Enablement: governance workflows that make engineering teams sustainably effective

Built for practitioners doing the actual work of responsible AI.

Reach out on LinkedIn LinkedIn

Popular repositories Loading

  1. bias-and-fairness-playbooks bias-and-fairness-playbooks Public

    Practical playbooks for AI/ML teams to detect and correct bias, assessment, root cause analysis, fairness metrics, and pre/in/post-processing interventions. Covers classical ML with EU AI Act, GDPR…

    1

  2. Yellow_responsive_layout Yellow_responsive_layout Public

    HTML

  3. React-tutorial React-tutorial Public

    JavaScript

  4. react-e-commerce-eco-product-site react-e-commerce-eco-product-site Public

    JavaScript

  5. Layout_test Layout_test Public

    JavaScript

  6. JS-Aviasales JS-Aviasales Public

    JavaScript