p
prachi_bhingare

Prachi Bhingare

@prachi_bhingare

Python AI Machine Learning Developer

Inde
Anglais, Hindi
Certaines informations sont présentées en anglais.
À propos de moi
AI/ML Engineer with 2+ years of experience building production RAG pipelines, LLM chatbots, and ML models. Currently work at Haptik improving enterprise information retrieval by 60%+. I help with: - RAG pipelines & AI chatbots (LangChain, OpenAI, FAISS) - ML models for prediction/classification (Scikit-learn, XGBoost) - Data analysis, EDA & visualization (Python) - AI web apps (FastAPI, Streamlit, Flask) - NLP & resume/document analysis tools Built 3+ end-to-end AI projects, all on GitHub (github.com/Pbhingare). I write clean, production-ready code and communicate clearly. Let's get started!... Plus d’infos

Compétences

p
prachi_bhingare
Prachi Bhingare
hors ligne • 
Temps de réponse moyen de 1 heure

Voir mes services

Développement de chatbots d'IA
I will build ai chatbot, rag pipeline, or llm app using python
De15 $US / projetPlus de détails
Intégrations IA
I will build a machine learning model for prediction using python
De90 $US / projetPlus de détails

Portfolio

Expérience professionnelle

Haptik

AI/ML Developer

Haptik • Temps plein

Jan 2024 - Present • 2 yrs 8 mos

Architected and deployed enterprise-grade RAG pipelines using LangChain, FAISS, and LLMs — improving document retrieval accuracy and reducing manual search effort across enterprise knowledge systems. Designed end-to-end document ingestion workflows including text extraction, chunking, embedding generation, vector indexing, and semantic retrieval, processing 10,000+ document chunks for scalable enterprise search. Integrated OpenAI and Hugging Face models to build context-aware question answering, conversational AI, and document summarization solutions used by enterprise clients. Optimized vector search, prompt engineering, and embedding workflows — reducing query latency by 40% and improving information retrieval efficiency by over 60%. Built FastAPI-based REST APIs and deployed AI-powered Streamlit and Gradio applications for internal and client-facing enterprise use cases. Maintained 90%+ response accuracy through model evaluation, debugging, and continuous system optimization. Collaborated with a 5-member Agile team and business stakeholders to translate enterprise requirements into scalable, production-ready AI workflows.