You profile has been submitted for review.
Chetan Khanna Gen AI and ML
No reviews yet
Results-driven Data Scientist with hands-on experience in designing and deploying scalable Machine Learning and Generative AI solutions across fraud analytics, risk monitoring, and intelligent document processing domains. Experienced in building end-to-end AI/ML pipelines involving large-scale data ingestion, preprocessing, feature engineering, model development, evaluation, and deployment using Python, SQL, and cloud-integrated workflows. Strong understanding of supervised and unsupervised learning, anomaly detection, predictive analytics, NLP, and transformer-based architectures.
Worked extensively on fraud detection and transaction monitoring models focused on identifying suspicious behavior patterns, anomaly detection, and risk scoring using structured and semi-structured datasets. Developed scalable data pipelines and automated analytical workflows to improve operational efficiency and model performance.
Designed and implemented Retrieval-Augmented Generation (RAG) based Document Intelligence systems enabling semantic document search, contextual question answering, and intelligent knowledge retrieval. Experience includes document chunking strategies, embedding generation, vector similarity search using FAISS, metadata filtering, reranking pipelines, and optimization of retrieval relevance using transformer-based embedding models and LLM frameworks. Also worked on batch embedding pipelines, GPU-optimized inference workflows, and scalable retrieval architectures for enterprise-scale document repositories.
Passionate about mentoring and teaching Data Science, Machine Learning, Deep Learning, and Generative AI concepts through practical implementation and real-world business use cases. Strong ability to simplify complex technical concepts while connecting theoretical understanding with industry-oriented applications and system design practices.
Worked extensively on fraud detection and transaction monitoring models focused on identifying suspicious behavior patterns, anomaly detection, and risk scoring using structured and semi-structured datasets. Developed scalable data pipelines and automated analytical workflows to improve operational efficiency and model performance.
Designed and implemented Retrieval-Augmented Generation (RAG) based Document Intelligence systems enabling semantic document search, contextual question answering, and intelligent knowledge retrieval. Experience includes document chunking strategies, embedding generation, vector similarity search using FAISS, metadata filtering, reranking pipelines, and optimization of retrieval relevance using transformer-based embedding models and LLM frameworks. Also worked on batch embedding pipelines, GPU-optimized inference workflows, and scalable retrieval architectures for enterprise-scale document repositories.
Passionate about mentoring and teaching Data Science, Machine Learning, Deep Learning, and Generative AI concepts through practical implementation and real-world business use cases. Strong ability to simplify complex technical concepts while connecting theoretical understanding with industry-oriented applications and system design practices.
Subjects
-
Machine learning model deployment using Flask and Streamlit Beginner-Expert
-
RAG (Retrieval-Augmented Generation) Beginner-Expert
-
Machine and Deep Learning project Beginner-Expert
Experience
-
Data Scientist (Nov, 2019–Present) at BARCLAYS NOIDA
Developed and deployed machine learning models for fraud detection, anomaly identification, and risk analysis using structured and unstructured data sources.
Monitored model performance, conducted validation and tuning, and ensured reliability, scalability, and compliance of deployed AI systems.
Built scalable data pipelines for data ingestion, preprocessing, feature engineering, and model training to support analytics and AI-driven applications.
Designed and implemented Retrieval-Augmented Generation (RAG) pipelines for document intelligence systems, enabling semantic search and contextual question answering.
Education
-
Bachelor's in Science (Jun, 2012–Jun, 2014) from CCS Meerut
Fee details
₹800–1,500/hour (US$8.42–15.79/hour)
For normal classes with theory and practice implementation - 800
For gaining experience on industry relevent projects and situations - 1500
-
-
Ghaziabad, Uttar Pradesh, India
-
Can travel:
No
-
- Last login: May 25
- Registered: May 25
- Total Teaching exp: 3.0 yrs.
- Teaches online: Yes
- Online Teaching exp: 0.0 yrs.
- Teaches at student's home: No
- Homework Help: Yes
-
Gender: Male
- Works as: Individual teacher
- Speaks: English, Hindi
- Trial Lesson: 1 hour
-
Fee:₹800–1,500/hour(USD 8.42–15.79/hour)
Reviews
No reviews yet. Be the first one to review this tutor.
