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

Hi, I'm Sai Nikhil Mendu, an AI/ML Engineer based in Saint Louis. I have 4 years of experience building end-to-end ML solutions, from data preprocessing to production deployment. I enjoy turning complex data into actionable insights and scalable systems. I'm proficient in Python, SQL, TensorFlow, PyTorch, and cloud services, and I thrive in fast-paced environments where models must perform in real time. I focus on feature engineering, hyperparameter tuning, and automating ML workflows to improve accuracy and reliability.…Hi, I'm Sai Nikhil Mendu, an AI/ML Engineer based in Saint Louis. I have 4 years of experience building end-to-end ML solutions, from data preprocessing to production deployment. I enjoy turning complex data into actionable insights and scalable systems. I'm proficient in Python, SQL, TensorFlow, PyTorch, and cloud services, and I thrive in fast-paced environments where models must perform in real time. I focus on feature engineering, hyperparameter tuning, and automating ML workflows to improve accuracy and reliability.

Sai Nikhil Mendu

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





Hi, I'm Sai Nikhil Mendu, an AI/ML Engineer based in Saint Louis. I have 4 years of experience building end-to-end ML solutions, from data preprocessing to production deployment. I enjoy turning complex data into actionable insights and scalable systems. I'm proficient in Python, SQL, TensorFlow, PyTorch, and cloud services, and I thrive in fast-paced environments where models must perform in real time. I focus on feature engineering, hyperparameter tuning, and automating ML workflows to improve accuracy and reliability.…Hi, I'm Sai Nikhil Mendu, an AI/ML Engineer based in Saint Louis. I have 4 years of experience building end-to-end ML solutions, from data preprocessing to production deployment. I enjoy turning complex data into actionable insights and scalable systems. I'm proficient in Python, SQL, TensorFlow, PyTorch, and cloud services, and I thrive in fast-paced environments where models must perform in real time. I focus on feature engineering, hyperparameter tuning, and automating ML workflows to improve accuracy and reliability.

Available to hire

Hi, I’m Sai Nikhil Mendu, an AI/ML Engineer based in Saint Louis. I have 4 years of experience building end-to-end ML solutions, from data preprocessing to production deployment. I enjoy turning complex data into actionable insights and scalable systems.

I’m proficient in Python, SQL, TensorFlow, PyTorch, and cloud services, and I thrive in fast-paced environments where models must perform in real time. I focus on feature engineering, hyperparameter tuning, and automating ML workflows to improve accuracy and reliability.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

AI/ML Engineer at JPMorgan Chase, USA

December 1, 2024 - Present

Built and deployed fraud and risk scoring models using Python, Scikit-learn, and PyTorch; improved detection accuracy by 18% and reduced false positives by 12% across high-volume transactions. Designed scalable ETL/ELT pipelines integrating transactional and behavioral datasets, reducing data processing time by 35% and increasing data availability for analytics teams. Developed Docker- and FastAPI-based real-time inference services, lowering model latency by 28% and supporting 24/7 fraud monitoring workloads. Automated model retraining, validation, and versioning using MLflow and CI/CD pipelines, cutting manual maintenance effort by 40% and improving deployment consistency. Integrated ML workloads with AWS (S3, EC2, Lambda), enhancing scalability and achieving 99.5% service uptime for production ML systems.

AI/ML Engineer at Persistent Systems, India

February 1, 2022 - July 1, 2023

Delivered classification, regression, and forecasting models for finance and healthcare clients, improving prediction accuracy by 15-25% through optimized feature engineering and cross-validation. Built end-to-end ML pipelines covering data ingestion, preprocessing, feature engineering, and evaluation, reducing pipeline failures by 30% and improving model stability. Developed NLP solutions using TensorFlow and HuggingFace, improving text classification and entity extraction performance by 20% across large unstructured datasets. Created Spark and Airflow data workflows enabling batch and near real-time processing, increasing data freshness and pipeline efficiency by 30%. Deployed ML models through REST APIs using FastAPI and Flask, reducing integration time by 40% and enabling seamless delivery to client applications.

ML Engineer at Synechron, India

June 1, 2020 - January 1, 2022

Prepared large structured and unstructured datasets using Python and SQL, reducing preprocessing time by 25% and improving data quality for model training. Built supervised and unsupervised models including classification, regression, and clustering, improving baseline performance by 20% across multiple internal projects. Performed feature engineering, hyperparameter tuning, and cross-validation, reducing overfitting by 18% and increasing model generalization. Developed scalable preprocessing scripts and repeatable workflows, enhancing data pipeline reliability by 30% and supporting continuous experimentation. Deployed lightweight ML models through Flask APIs, enabling quick integration and reducing deployment turnaround time by 35%.

AI/ML Engineer at JPMorgan Chase

December 1, 2024 - Present

Built and deployed fraud and risk scoring models using Python, Scikit-learn, and PyTorch, improving detection accuracy by 18% and reducing false positives by 12% across high-volume transactions. Designed scalable ETL/ELT pipelines integrating transactional and user-behavior datasets, reducing data processing time by 35% and increasing data availability for analytics teams. Developed Docker- and FastAPI-based real-time inference services, lowering model latency by 28% and supporting 24/7 fraud monitoring workloads. Automated model retraining, validation, and versioning using MLflow and CI/CD pipelines, cutting manual maintenance effort by 40% and improving deployment consistency. Integrated ML workloads with AWS (S3, EC2, Lambda), enhancing scalability and achieving 99.5% service uptime for production ML systems.

AI/ML Engineer at Persistent Systems

February 1, 2022 - July 1, 2023

Delivered classification, regression, and forecasting models for finance and healthcare clients, improving prediction accuracy by 15–25% through optimized feature engineering and cross-validation. Built end-to-end ML pipelines covering data ingestion, preprocessing, feature engineering, and evaluation, reducing pipeline failures by 30% and improving model stability. Developed NLP solutions using TensorFlow and HuggingFace, improving text classification and entity extraction performance by 20% across large unstructured datasets. Created Spark and Airflow data workflows enabling batch and near-real-time processing, increasing data freshness and pipeline efficiency by 30%. Deployed ML models through REST APIs (FastAPI/Flask), reducing integration time by 40% and enabling seamless delivery to client applications.

ML Engineer at Synechron

June 1, 2020 - January 1, 2022