class PratimaKumari:
def __init__(self):
self.name = "Pratima Kumari"
self.role = "AI Engineer & Full-Stack Developer"
self.interests = ["AI/ML", "NLP", "Data Science", "Web Development"]
self.currently_learning = ["LLM Evaluation", "AI Safety", "MLOps"]
self.fun_fact = "I build systems that check if AI is telling the truth! 🔍"
def say_hi(self):
print("Thanks for visiting my profile! Let's build something amazing together.")
me = PratimaKumari()
me.say_hi()| Project | Domain & Focus | Live Repositories |
|---|---|---|
| 🔍 AI Hallucination & Factuality Detection System | Evidence verification, NLP factuality scoring, 5-type error taxonomy | View Repo |
| 📊 LLM Response Evaluation & Benchmarking | 120+ prompts, 7-dimensional rubrics, Bradley-Terry Elo tournament | View Repo |
| 💻 AI Code Evaluation & Benchmarking System | Multilingual (Py/JS/TS/C++) 10-criteria evaluation, CWE security audits | View Repo |
- 🔍 AI Hallucination Detection — Building systems to evaluate and validate AI-generated content
- 🧠 LLM Evaluation Pipelines — Researching methods for factuality scoring and error taxonomy
- 📊 Data Validation Systems — Creating tools for AI Quality Assurance
- 🌐 Full-Stack Web Apps — Building premium, interactive web applications
| Area | Skills |
|---|---|
| 🤖 AI/ML | NLP, LLM Evaluation, Hallucination Detection, Factuality Scoring |
| 📊 Data Science | Data Analysis, Statistical Modeling, Data Validation, Visualization |
| 🔍 Quality Assurance | AI Output Validation, Error Taxonomy, Claim Verification |
| 💻 Development | Full-Stack Web Apps, REST APIs, Interactive Dashboards |
| 🛠️ Engineering | Clean Architecture, CI/CD, Testing, Documentation |
