I am Manideep Yasala, an AI/ML Engineer based in Texas with 4+ years of experience building and deploying scalable ML and Generative AI solutions in financial services and cloud environments. I specialize in delivering end-to-end data pipelines, real-time inference systems, and production-grade APIs using Python, SQL, PySpark, and FastAPI. My work includes XGBoost and ensemble methods, NLP and transformer architectures (BERT, GPT, LLaMA), and LLM-driven applications with RAG pipelines, LangChain, and vector databases like FAISS and Pinecone. I also follow MLOps best practices with MLflow, Docker, CI/CD, and cloud platforms (AWS, GCP, Azure) to train, deploy, and monitor models at scale.

Manideep Yasala

I am Manideep Yasala, an AI/ML Engineer based in Texas with 4+ years of experience building and deploying scalable ML and Generative AI solutions in financial services and cloud environments. I specialize in delivering end-to-end data pipelines, real-time inference systems, and production-grade APIs using Python, SQL, PySpark, and FastAPI. My work includes XGBoost and ensemble methods, NLP and transformer architectures (BERT, GPT, LLaMA), and LLM-driven applications with RAG pipelines, LangChain, and vector databases like FAISS and Pinecone. I also follow MLOps best practices with MLflow, Docker, CI/CD, and cloud platforms (AWS, GCP, Azure) to train, deploy, and monitor models at scale.

Available to hire

I am Manideep Yasala, an AI/ML Engineer based in Texas with 4+ years of experience building and deploying scalable ML and Generative AI solutions in financial services and cloud environments.

I specialize in delivering end-to-end data pipelines, real-time inference systems, and production-grade APIs using Python, SQL, PySpark, and FastAPI. My work includes XGBoost and ensemble methods, NLP and transformer architectures (BERT, GPT, LLaMA), and LLM-driven applications with RAG pipelines, LangChain, and vector databases like FAISS and Pinecone. I also follow MLOps best practices with MLflow, Docker, CI/CD, and cloud platforms (AWS, GCP, Azure) to train, deploy, and monitor models at scale.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
See more

Work Experience

AI/ML Engineer at PNC Bank
February 1, 2025 - Present
Architected the Enterprise Fraud Detection Intelligence Platform, incorporating Generative AI capabilities using LLMs and RAG pipelines (LangChain, FAISS) to generate contextual fraud insights from transactional data. Engineered scalable data pipelines using Python, PySpark, and distributed processing frameworks to ingest, transform, and analyze high-volume financial transaction data. Developed robust classification models using XGBoost and ensemble techniques to identify fraudulent patterns, improving detection accuracy by 21% across digital channels. Implemented high-performance inference services using FastAPI and RESTful APIs to operationalize ML and GenAI models within secure banking environments. Constructed transformer-based semantic analysis workflows leveraging embeddings and vector search to automate anomaly detection and generate investigation-ready summaries. Optimized deployment pipelines by containerizing models with Docker and managing lifecycle using MLflow and AWS Sage
ML Engineer at VMware
May 1, 2020 - December 31, 2022
Engineered the Intelligent Log Anomaly Detection Platform project to create scalable ML solutions for monitoring cloud-based log data. Designed and developed end-to-end machine learning models using Python and Scikit-learn for anomaly detection and predictive insights in distributed systems. Implemented NLP-based pipelines using Hugging Face Transformers to process unstructured log data and improve pattern recognition capabilities. Built scalable data processing workflows using PySpark to handle high-volume log ingestion and feature engineering across multiple data sources. Integrated RESTful APIs using FastAPI to deploy ML models into production and enable real-time inference for monitoring systems. Optimized model performance through hyperparameter tuning and ensemble methods, improving anomaly detection accuracy by 18%. Deployed and managed models on AWS SageMaker with CI/CD pipelines, reducing model deployment time by 30%. Collaborated with DevOps and cloud engineering teams to imp

Education

Master of Science in Computer Science at University of North Texas
January 1, 2023 - December 31, 2024

Qualifications

Add your qualifications or awards here.

Industry Experience

Financial Services, Software & Internet, Professional Services

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
See more