Skip to content
View SaiTeja-Erukude's full-sized avatar
🎯
Focusing
🎯
Focusing
20 followers · 6 following

Block or report SaiTeja-Erukude

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
SaiTeja-Erukude/README.md

Sai Teja Erukude

Data Scientist | AI Researcher | Responsible AI & AI Security Practitioner

Sai works at the intersection of applied AI, responsible AI, computer vision, LLM safety, and research-driven open-source tooling. His work focuses on building trustworthy AI systems that can be evaluated, audited, and deployed with greater confidence.

Areas of Focus

  • Responsible AI and trustworthy machine learning
  • AI security, LLM safety, and agentic AI risk assessment
  • ML, LLM, and agentic system auditing, evaluation, and red-teaming
  • Bias detection, fairness assessment, and explainability
  • Computer vision dataset quality, robustness, and model reliability
  • Scientific AI for astronomy, healthcare, and other high-impact domains
  • Research-backed open-source tools for AI evaluation, monitoring, and governance

Featured Open-Source Projects

Project Description
rai-audit Python package suite for evidence-grade audits of responsible, secure, and trustworthy AI systems
promptsanitizer Security-focused Python toolkit for detecting and mitigating secrets, PII, prompt injection, and RCE risks in AI pipelines
agentdog Pytest-style evaluation toolkit for testing and assessing AI agent behavior
cv-quality Computer vision dataset quality toolkit for identifying annotation, image, and dataset issues
Enhancing-Ground-Based-Astronomy-using-GenAI Generative AI approach for improving ground-based astronomy image quality

Research, Writing, and Professional Work

Sai publishes and reviews technical work across AI, responsible AI, computer vision, medical imaging, astronomy, and applied machine learning. His work focuses on connecting research, engineering, and practical AI governance.

Collaboration

Sai is interested in open-source collaboration, research-driven engineering, and applied AI systems that create measurable real-world impact.

The goal is to make AI systems easier to evaluate, audit, secure, and report across practical engineering workflows.

Pinned Loading

  1. rai-audit rai-audit Public

    A Python package suite for generating evidence-grade audits of responsible, secure, and trustworthy AI systems.

    Python 14 1

  2. promptsanitizer promptsanitizer Public

    Secrets firewall for AI pipelines — redact credentials and PII before they reach (or leave) LLMs.

    Python 13

  3. agentdog agentdog Public

    AgentDog helps developers inspect, test, score, and monitor AI agent runs locally.

    Python 5

  4. cv-quality cv-quality Public

    A Python toolkit for cleaner datasets in computer vision.

    Python 2

  5. Enhancing-Ground-Based-Astronomy-using-GenAI Enhancing-Ground-Based-Astronomy-using-GenAI Public

    Amplifying the imaging power of ground-based telescopes with space-based telescopes data and generative AI.

    Python 2

  6. identifying-bias-in-dnn-classification identifying-bias-in-dnn-classification Public

    Identifying dataset biases, contextual information, and background noise in DNNs for reliable performance evaluation.

    Python