Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Poojitha Lysetti, an AI/ML Engineer with 4 years of hands-on experience in building and deploying machine learning, deep learning, and generative AI solutions. I specialize in NLP, computer vision, and predictive analytics, and I have led end-to-end development from model prototyping to production deployment using Python, TensorFlow, PyTorch, and Scikit-learn. In my current role at JPMorgan Chase & Co., I designed scalable LLM pipelines and RAG systems to automate document intelligence and accelerate risk and compliance workflows. Previously, at LTIMindtree, I built supervised and deep learning models for churn prediction, fraud detection, and NLP tasks, while delivering robust ETL, feature engineering, and dashboard monitoring.…I am Poojitha Lysetti, an AI/ML Engineer with 4 years of hands-on experience in building and deploying machine learning, deep learning, and generative AI solutions. I specialize in NLP, computer vision, and predictive analytics, and I have led end-to-end development from model prototyping to production deployment using Python, TensorFlow, PyTorch, and Scikit-learn. In my current role at JPMorgan Chase & Co., I designed scalable LLM pipelines and RAG systems to automate document intelligence and accelerate risk and compliance workflows. Previously, at LTIMindtree, I built supervised and deep learning models for churn prediction, fraud detection, and NLP tasks, while delivering robust ETL, feature engineering, and dashboard monitoring.

Poojitha Lysetti

AI Engineer, Data Scientist, Full Stack Developer, +2





I am Poojitha Lysetti, an AI/ML Engineer with 4 years of hands-on experience in building and deploying machine learning, deep learning, and generative AI solutions. I specialize in NLP, computer vision, and predictive analytics, and I have led end-to-end development from model prototyping to production deployment using Python, TensorFlow, PyTorch, and Scikit-learn. In my current role at JPMorgan Chase & Co., I designed scalable LLM pipelines and RAG systems to automate document intelligence and accelerate risk and compliance workflows. Previously, at LTIMindtree, I built supervised and deep learning models for churn prediction, fraud detection, and NLP tasks, while delivering robust ETL, feature engineering, and dashboard monitoring.…I am Poojitha Lysetti, an AI/ML Engineer with 4 years of hands-on experience in building and deploying machine learning, deep learning, and generative AI solutions. I specialize in NLP, computer vision, and predictive analytics, and I have led end-to-end development from model prototyping to production deployment using Python, TensorFlow, PyTorch, and Scikit-learn. In my current role at JPMorgan Chase & Co., I designed scalable LLM pipelines and RAG systems to automate document intelligence and accelerate risk and compliance workflows. Previously, at LTIMindtree, I built supervised and deep learning models for churn prediction, fraud detection, and NLP tasks, while delivering robust ETL, feature engineering, and dashboard monitoring.

Available to hire

I am Poojitha Lysetti, an AI/ML Engineer with 4 years of hands-on experience in building and deploying machine learning, deep learning, and generative AI solutions. I specialize in NLP, computer vision, and predictive analytics, and I have led end-to-end development from model prototyping to production deployment using Python, TensorFlow, PyTorch, and Scikit-learn.

In my current role at JPMorgan Chase & Co., I designed scalable LLM pipelines and RAG systems to automate document intelligence and accelerate risk and compliance workflows. Previously, at LTIMindtree, I built supervised and deep learning models for churn prediction, fraud detection, and NLP tasks, while delivering robust ETL, feature engineering, and dashboard monitoring.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Work Experience

AI/ML Engineer at JPMorgan Chase & Co. USA

October 1, 2024 - November 18, 2025

Developed and deployed large language model (LLM) pipelines using LangGraph, LlamaIndex, and GPT-4 to automate document intelligence for financial compliance reports, reducing manual review time by 42%. Engineered a Retrieval-Augmented Generation (RAG) system integrated with Pinecone and FAISS to retrieve unstructured credit data with under 1-second latency, improving analyst decision accuracy by 31%. Trained and fine-tuned transformer models (BERT, LLaMA, Claude) for Named Entity Recognition (NER) achieving 96% precision. Implemented scalable TensorFlow pipelines on AWS SageMaker for customer risk scoring, reducing training costs by 28%. Automated data ingestion and preprocessing with PySpark and PostgreSQL, enabling near real-time analytics for fraud detection and improving pipeline throughput by 2.3x. Orchestrated containerized deployments via Docker, AWS Lambda, and CI/CD, ensuring consistent and version-controlled model releases across environments by 30%. Delivered Tableau dashbo

Machine Learning Engineer at LTIMindtree India

July 1, 2023 - July 1, 2023

Designed and trained supervised models (Decision Trees, Random Forest, Naive Bayes, XGBoost) to predict customer churn and loan default risk with 89% accuracy, reducing manual review duration by 35%. Built deep learning architectures with RNNs and CNNs for sentiment and image classification, improving F1-score by 22% over baselines. Implemented unsupervised clustering (K-means, DBSCAN) and PCA to segment transaction data and detect anomalies, identifying fraud clusters previously missed by rule-based systems by 60%. Optimized NLP workflows using BERT, NLTK, and SpaCy for entity recognition and intent analysis, enhancing text classification precision by 30%. Streamlined ETL and feature engineering with PySpark and SQL Server, reducing data preparation time by 40% and improving overall model retraining efficiency. Delivered Power BI dashboards integrated with Azure ML APIs to monitor metrics and visualize model drift across production environments by 35%.

AI/ML Engineer at JPMorgan Chase & Co.

October 1, 2024 - Present

Developed and deployed LLM pipelines using LangGraph, LlamaIndex, and GPT-4 to automate document intelligence for financial compliance reports, reducing manual review time by 42%. Engineered a Retrieval-Augmented Generation (RAG) system integrated with Pinecone and FAISS to retrieve unstructured credit data with under 1-second latency, improving analyst decision accuracy by 31%. Trained and fine-tuned transformer models (BERT, LLaMA, Claude) for Named Entity Recognition (NER) to extract entities from trade confirmations and contracts with 96% precision. Implemented scalable TensorFlow pipelines on AWS SageMaker for customer risk scoring, cutting model training cost by 28%. Automated data ingestion and preprocessing using PySpark and PostgreSQL, enabling near real-time analytics for fraud detection and enhancing pipeline throughput by 2.3×. Orchestrated containerized deployments via Docker, AWS Lambda, and CI/CD workflows, ensuring consistent and version-controlled model releases acros

Machine Learning Engineer at LTIMindtree

August 1, 2020 - July 1, 2023

Designed and trained supervised models using Decision Trees, Random Forests, Naive Bayes, and XGBoost to predict customer churn and loan default risk, achieving 89% accuracy and reducing manual review duration by 35%. Developed deep learning architectures with RNNs and CNNs in Keras and PyTorch for sentiment and image classification, improving F1-score by 22%. Implemented unsupervised algorithms such as K-Means, DBSCAN, and PCA to segment transaction data and detect anomalies, identifying fraud clusters missed by rule-based systems by 60%. Optimized NLP workflows using BERT, NLTK, and SpaCy for entity recognition and intent analysis, enhancing text classification precision by 30%. Streamlined ETL and feature engineering with PySpark and SQL Server, reducing data preparation time by 40% and improving model retraining efficiency. Performed EDA and hypothesis testing with Python, NumPy, Pandas, and Excel, uncovering actionable insights that reduced operational costs by 15%. Delivered dash