Skip to content
View Priyrajsinh's full-sized avatar
☕
☕
  • Bhavnagar
  • 17:47 (UTC -12:00)

Block or report Priyrajsinh

Report abuse

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

Report abuse
Priyrajsinh/README.md

Machine Learning Engineer Header

Core Competencies

Machine Learning & Data Python · NumPy · Pandas · Scikit-Learn · PyTorch · Matplotlib

ML Engineering Model evaluation · Feature pipelines · Experimentation · Research implementation

Web & Systems React · TypeScript · JavaScript · PHP · SQL · Socket.io

Socials

Instagram LinkedIn Medium

Priyrajsinh


Pinned Loading

  1. causal-ml-hte causal-ml-hte Public

    OLS on observational data says job training hurts earnings. Double ML corrects the bias and recovers the $1,794 RCT ground truth. Per-individual CATE · SHAP moderators · FastAPI · Streamlit dashboard.

    Python

  2. Conformal-Prediction-Uncertainty-Aware-Medical-AI Conformal-Prediction-Uncertainty-Aware-Medical-AI Public

    Coverage-guaranteed medical AI: XGBoost + MAPIE conformal prediction on UCI Heart Disease. FastAPI · Gradio · Streamlit · Prometheus · MLflow.

    Python

  3. Hybrid-LLM-Jailbreak-Detector Hybrid-LLM-Jailbreak-Detector Public

    Defense-in-depth input safety for LLMs — perplexity gate + FAISS + ModernBERT + LoRA + Llama Guard 3, behind a deterministic policy gate. 99.88% accuracy, 99.47% jailbreak recall, calibrated confi…

    Python

  4. RealTime-ML-Drift-Monitoring RealTime-ML-Drift-Monitoring Public

    Real-time ML model drift detection — PSI, KS test, SHAP, Evidently, Prometheus, Grafana, Alertmanager, FastAPI, Streamlit

    Python

  5. semantic-hybrid-search semantic-hybrid-search Public

    Semantic Hybrid Search with Sentence-Transformers + FAISS. Ask any question in plain English. Get the most relevant Wikipedia passages back — ranked by meaning, not just keywords.

    Python

  6. -XGBoost-SHAP-Explainability-Dashboard -XGBoost-SHAP-Explainability-Dashboard Public

    Built an end-to-end classification pipeline on the Pima Indians Diabetes dataset with XGBoost, Optuna hyperparameter optimization, and comprehensive SHAP explainability. Deployed as a multi-tab St…

    HTML