Prasanth

Machine Learning Engineer with 4+ years of experience designing, developing, and deploying AI/ML applications and cloud-native software on AWS. Experienced in building LLM-powered applications using LangChain, LangGraph, Retrieval-Augmented Generation (RAG), and Hugging Face, along with production ML solutions using TensorFlow, PyTorch, and Scikit-learn. Skilled in developing FastAPI-based microservices, scalable data pipelines, and MLOps workflows using Docker, Kubernetes, MLflow, and SageMaker, delivering enterprise AI solutions that automate workflows and support production-scale deployments.

Machine Learning Engineer - AI Product Studio

(2025-06)

• Built multi-agent AI applications using Python, LangChain, LangGraph, GPT-4, and Claude to automate document analysis and workflow orchestration, improving response consistency across enterprise business processes.
• Implemented Retrieval-Augmented Generation (RAG) pipelines using Pinecone, FAISS, hybrid search, and embedding models, improving retrieval precision by approximately 30% and reducing hallucinations in enterprise knowledge systems.
• Delivered scalable AI microservices using FastAPI and Flask with asynchronous REST APIs, reducing inference latency by approximately 35% while enabling reliable model inference and enterprise application integration.
• Optimized distributed PySpark, Airflow, and dbt data pipelines that processed large-scale datasets for AI applications, improving pipeline reliability and reducing data preparation time.
• Automated MLOps workflows using MLflow, SageMaker Pipelines, Docker, Kubernetes, Jenkins, and GitHub Actions, streamlining model versioning, validation, and continuous deployment across environments.
• Deployed cloud-native AI services on AWS using SageMaker, Lambda, EC2, API Gateway, S3, and DynamoDB, enabling scalable inference, reliable service integration, and production-ready deployments.

Applied AI Engineer - Morgan Stanley

(2024-07 - 2025-05)

• Engineered end-to-end machine learning pipelines spanning data ingestion, feature engineering, model training, deployment, and monitoring, reducing model delivery time by approximately 40% across financial risk analytics workflows.
• Delivered LLM-powered multi-agent solutions using LangChain, LangGraph, GPT-4, Claude, and AWS Bedrock to automate financial document analysis and strengthen compliance review workflows.
• Optimized distributed PySpark and SQL data pipelines processing large-scale financial datasets, improving data reliability and reducing ETL processing latency for downstream analytics.
• Automated ML lifecycle management using MLflow, SageMaker Pipelines, Docker, Kubernetes, and Jenkins, reducing model deployment effort by approximately 50% while standardizing CI/CD workflows.
• Integrated AWS services including S3, Lambda, and Bedrock with AI applications to support secure, scalable inference pipelines and enterprise-grade model deployment.

Associate Engineer - Virtusa

(2022-06 - 2023-06)

• Modernized backend services by implementing scalable RESTful microservices using FastAPI and Flask, improving application performance and supporting reliable enterprise integrations.
• Engineered distributed ETL pipelines using PySpark and SQL to process large-scale enterprise datasets, improving data pipeline efficiency and supporting downstream reporting and business applications.
• Containerized backend services using Docker and Kubernetes, streamlining deployment workflows and improving application reliability across development and testing environments.
• Enhanced REST API performance through query optimization, efficient data access patterns, and backend improvements, reducing response times for enterprise applications.
• Strengthened application quality by implementing automated testing with PyTest and monitoring services with AWS CloudWatch, improving system reliability and accelerating issue detection.

Software Engineer - Cognizant

(2021-05 - 2022-05)

• Developed backend services and RESTful APIs using Python and Flask, enabling secure communication between enterprise applications and improving application maintainability.
• Optimized distributed ETL pipelines using PySpark and SQL to process large-scale enterprise datasets, improving data consistency and supporting downstream reporting workflows.
• Deployed backend applications on AWS using EC2, Lambda, API Gateway, and DynamoDB, improving scalability and supporting reliable cloud-based application deployments.
• Streamlined application delivery by implementing CI/CD pipelines using Jenkins and GitHub Actions, improving release consistency and reducing manual deployment effort.
• Containerized backend applications using Docker and collaborated on Kubernetes-based deployments, improving deployment consistency across development and testing environments.

Master of Science - Computer Science - University of Central Missouri (2023-08 - 2025-05)

Bachelor of Technology - Electrical and Electronics Engineering - CVR College of Engineering (2018-08 - 2022-05)