Machine Learning Ml Engineer

Vidit Hemant Hirve

AI/ML Engineer

Email: ***********@*****.*** Contact: 602-***-**** LinkedIn

Summary

AI/ML Engineer with 3+ years of extensive experience in developing and deploying machine learning models, utilizing a range of technologies to drive business outcomes. Skilled in predictive modeling, data analysis, and automation, with expertise in cloud platforms like AWS and tools like Python, Snowflake, and various AI frameworks. Strong practice in model optimization, real-time system integration, and MLOps practices. Adept at solving complex problems and improving operational efficiencies with diverse industries, and focus on scalable AI solutions and data-driven decision-making. Experience

3 Enrollment Marketing, Inc, USA Feb 2025 – Current AI Engineer

• Collaborated with marketing teams to identify and target high school students (Sophomores, Juniors, Seniors) for university enrollment, leveraging predictive modeling to determine ideal student lists using AWS tools and Python programming.

• Developed predictive models using AWS Sagemaker, S3, Lambda, and Python to identify ideal student prospects, helping clients purchase targeted student lists based on individual university strengths and specific enrollment goals.

• Created dynamic email content using AI models (GPT 4.5/Claude 3.7) for personalized student and parent marketing campaigns, automating email content generation with AWS Bedrock, Lambda, and S3 to increase engagement and conversions.

• Automated the process of sending marketing emails and scheduling appointments based on call transcript data, using AWS services, Python, and AI technologies to optimize client engagement and streamline communication processes.

• Utilized Snowflake for data storage and management, enabling efficient handling of large datasets, ensuring seamless integration across projects, and optimizing the data flow between different marketing and AI initiatives within the company. DXC Technology, USA Jan 2024 – Dec 2024

AI Engineer

• Designed and deployed a multi-class image classification system using convolutional neural networks (CNNs) to identify defects in manufacturing, reducing manual inspection time by 40%. This system utilized transfer learning to minimize training time and improve scalability.

• Developed a self-supervised learning framework to augment data from limited labeled datasets, resulting in a 25% increase in prediction accuracy, enabling more effective decision-making in production lines.

• Applied TensorRT and ONNX model optimization techniques, achieving a 50% reduction in inference time for real-time, low-latency applications in edge devices. This significantly improved processing speed in time-sensitive manufacturing environments.

• Integrated GAN-based synthetic data generation to enhance the model’s ability to detect rare defects, reducing data collection costs and improving accuracy for edge cases by 15%.

• Built an automated MLOps pipeline using MLflow, Kubernetes, and Jenkins, which streamlined model versioning, deployment, and monitoring across multiple cloud environments, ensuring high availability and scalability of AI services.

• Designed a real-time anomaly detection system using autoencoders and LSTM networks to detect unexpected events during manufacturing, improving the response time for critical failures by 30%.

• Leveraged AWS Lambda and Amazon SageMaker to deploy scalable AI models, automating continuous model retraining based on feedback loops from production data, driving a 20% improvement in model robustness.

• Established a predictive maintenance system using time-series analysis and Recurrent Neural Networks (RNNs), reducing unplanned equipment downtime by 25% and extending machine life cycles. Wipro Enterprises - India Jan 2020 – Jul 2022

Machine Learning Engineer

• Led the design of a recommendation engine based on collaborative filtering and content-based filtering techniques, which increased user engagement by 20% and enhanced personalization for an e-commerce platform.

• Developed an NLP-based text classification system for customer sentiment analysis using transformer-based architectures (BERT, GPT-3), improving the accuracy of feedback categorization by 30% and optimizing product recommendation strategies.

• Engineered an unsupervised clustering model using K-Means and DBSCAN for segmenting customers, allowing the marketing team to better target promotions and improve retention rates by 15%.

• Spearheaded the development of a fraud detection model utilizing anomaly detection algorithms and one-class SVM, resulting in a 25% reduction in financial fraud cases for a banking client.

• Implemented a reinforcement learning algorithm to optimize inventory management for a retail company, improving stock turnover by 10% and reducing excess inventory costs.

• Built a dynamic pricing model using multi-variable regression and Bayesian optimization, allowing an e-commerce client to optimize pricing strategies and increase revenue by 12%.

• Automated model deployment using Docker, Kubernetes, and Azure DevOps, ensuring continuous integration and delivery of machine learning models in a cloud-native environment.

• Collaborated with cross-functional teams to deploy graph neural networks (GNNs) for fraud detection in large transaction datasets, improving the identification of anomalous behavior by 20%.

• Integrated stream processing frameworks like Apache Kafka with real-time prediction pipelines, ensuring low-latency model inference for live customer interaction applications.

Skills

• Machine Learning & AI: Predictive Modeling, Supervised & Unsupervised Learning, Reinforcement Learning, Natural Language Processing (NLP), Computer Vision, Anomaly Detection, Time-Series Forecasting

• AI Tools & Technologies: AWS (SageMaker, Lambda, S3, Bedrock), GPT-4.5, Claude 3.7, TensorRT, ONNX, MLflow, Kubernetes, Jenkins

• Programming Languages: Python, SQL, R

• Data Engineering: Snowflake, Apache Kafka, Data Storage & Management

• Model Deployment & Automation: Docker, Kubernetes, Azure DevOps, MLOps, Continuous Integration/Delivery (CI/CD)

• Deep Learning Frameworks: TensorFlow, PyTorch, Keras, Transfer Learning, CNNs, LSTMs, RNNs, GANs

• Cloud & DevOps: AWS Lambda, Amazon SageMaker, Jenkins, Kubernetes, Docker

• Data Analysis: Feature Engineering, Data Preprocessing, Data Augmentation

• Other Technologies: BERT, GPT-3, Graph Neural Networks (GNNs), K-Means, DBSCAN, One-Class SVM, Multi-Variable Regression Education

Master of Science in Robotics and Autonomous Systems Arizona State University, Tempe, Arizona, USA – May 2024 Relevant Coursework: Deep Neural Networks, Perception in Robotics, Multi-Robot Systems, Optimal Control BSc in Electronic Science

Savitribai Phule Pune University, India – May 2020 Relevant Coursework: Embedded Systems, Power Electronics, Industrial Process Control

Contact this candidate