Amogha G

About Amogha G

AI/ML Engineer with 4+ years of experience building scalable machine learning and…

Experience

1. Ai Ml Engineer

   Kroger

   Nov 2024 — Present · US

   Deployed a calibrated LightGBM cart-return propensity ML model with a nightly batch scorer to the data lake and customer- level scores, added AUC and drift monitors, and used scikit-learn for preprocessing and isotonic calibration • Enhanced existing customer segmentation by implementing supervised propensity modeling in TensorFlow and Keras and unsupervised k-prototypes and HDBSCAN to enable targeted promotions • Augmented the existing recommendation system by combining matrix factorization for candidate generation and item–item collaborative filtering for “also bought” and added cold-start coverage with Hugging Face sentence-transformer embeddings in PyTorch, improving Hit@K and NDCG offline and supporting A/B evaluation under predefined guardrails • Applied NLP with NLTK and Hugging Face Transformers to extract aspect-level sentiment from product reviews and customer feedback and integrated a review-based score into search ranking and early inventory alerts • Piloted a Gen AI and NLP policy assistant using an LLM with RAG over policy and FAQ documents with Hugging Face embeddings and a FAISS vector index and added PII redaction and source citations while delivering responses through internal REST APIs • Enhanced fraud scoring with graph-derived relational features on a CatBoost classifier and applied time-aware cross- validation with SHAP explanations and KS and PR-AUC monitoring to reduce false positives at fixed recall