Jesse Davis
About
Detail
Senior Software Engineer
Crossville, Tennessee, United States
Résumé
Jobs
verified_user
0% verified
Senior Software Engineer | Agentic AI EngineerOracleSep 2023 - Feb 2026 (2 years 6 months)• Spearheaded the development of GenAI applications using Vertex AI and Gemini models, delivering advanced conversational AI, text summarization, classification, and agent workflows for enterprise healthcare solutions. • Designed and implemented RAG pipelines and vector search workflows using tools like LangChain, LlamaIndex, Pinecone, and FAISS, enabling AI models to retrieve contextual information from knowledge bases. • Developed data ingestion and preprocessing pipelines with Python, REST APIs, and web scraping, structuring datasets for LLM training, fine-tuning, and RAG knowledge bases. • Deployed AI services on cloud infrastructure with Docker and Kubernetes, supporting scalable inference and containerized microservice architectures—p- Software Engineer | AI/ML DeveloperAutodeskJan 2021 - Jun 2023 (2 years 6 months)• Developed and deployed deep learning models for customer segmentation, recommendation systems, and predictive analytics using Keras and TensorFlow. • Collaborated with data engineering teams to build data pipelines using SQL, PostgreSQL, and BigQuery, enabling reliable data ingestion and preparation for machine learning workflows and analytics. • Implemented data preprocessing and feature engineering pipelines, applying techniques such as PCA, t-SNE, and clustering for dimensionality reduction, data exploration, and improved model training. • Developed machine learning models for customer behavior prediction and marketing optimization, including linear and non-linear regression, SVM, and random forest, enabling more accurate forecasting a
- Software DeveloperSalesforceJul 2015 - Dec 2020 (5 years 6 months)• Developed and improved recommendation systems using collaborative filtering and content-based algorithms, increasing user engagement across customer-facing product features. • Built data preprocessing and feature engineering pipelines using Python, Pandas, and NumPy, applying dimensionality reduction techniques such as PCA and t-SNE to improve model performance on large datasets. • Implemented machine learning models using Scikit-learn and TensorFlow for tasks including customer behavior prediction, text classification, and image analysis. • Conducted A/B testing and statistical hypothesis testing to evaluate model performance and measure the impact of machine learning features on product metrics. • Designed and maintained automated ML wo
- Full Stack DeveloperIntellectsoftJan 2010 - Jun 2015 (5 years 6 months)• Assisted in developing and deploying machine learning models using Python and TensorFlow for predictive analytics and data classification tasks. • Contributed to the development of backend services using Node.js and Express, integrating machine learning models into scalable applications. • Assisted in frontend development with React and Vue.js, ensuring smooth integration between UI and backend services. • Collaborated with senior engineers to integrate models into existing RESTful APIs and microservices. • Built and optimized data pipelines using Flask and Django, and deployed models in production using Docker and Kubernetes for scalable solutions. • Developed and optimized SQL queries for data extraction, working with MySQL and PostgreS
Education
verified_user
0% verified
- MBachelor's Degree in Computer ScienceMiddle Tennessee State University (MTSU)Aug 2004 - May 2009 (4 years 10 months)
Projects (professional or personal)
verified_user
0% verified
- AAI-Powered Knowledge Automation Platform (MCP + RAG + LLM Integration)Tech Stack: Model Context Protocol (MCP), Retrieval-Augmented Generation (RAG), LLM APIs (OpenAI / Claude), Milvus, Python, FastAPI, ReactJS • Designed and implemented a Retrieval-Augmented Generation (RAG) system that retrieves relevant knowledge from enterprise documents and databases, enabling context-aware responses for user queries. • Built an MCP-based integration layer allowing AI agents to securely interact with enterprise tools and external systems, transforming user requests into executable operations across multiple services. • Developed document ingestion pipelines that parse, clean, and split large datasets, generating embeddings and storing them in a vector database to enable fast semantic search and contextual retrieval. • In
- GGenerative AI Customer Support Agent with RAGTech Stack: LangChain, LangGraph, FAISS, Flask, Jenkins, Datadog • Engineered a domain-specific chatbot for automated support with semantic search over internal documentation, reducing average response time by 25%. • Integrated multi-agent workflows via LangGraph for knowledge extraction and FAQ generation, lowering time-to-market for new features by 20%. • Implemented CI/CD pipelines with GitHub Actions and Jenkins, adding real-time monitoring with Datadog to track performance drift and ensure high availability.
- PPredictive Maintenance & Conversational AI AssistantTech Stack: PyTorch, XGBoost, LLaMA-2, LangChain, AWS SageMaker, ReactJS • Developed ML models for predictive maintenance, using XGBoost and deep learning to detect early signs of equipment failure with 87%+ accuracy. • Integrated a conversational AI agent powered by LLaMA-2 + LangChain that provided technicians with natural language insights, troubleshooting guidance, and contextual explanations. • Implemented continuous feedback loops for retraining, achieving 20% faster issue resolution and 85%+ user satisfaction. • Deployed via SageMaker with ReactJS front-end for real-time operator interaction.
- SScalable Notification Intelligence SystemTech Stack: PyTorch, XGBoost, TensorFlow, PostgreSQL, SageMaker • Developed predictive models for notification prioritization and unread message forecasting, increasing user engagement by 25%. • Combined supervised ML models (XGBoost, SVM, Random Forest) with deep learning approaches for context-aware predictions. • Integrated into customer-facing apps with containerized microservices, orchestrated deployments on AWS, and real-time monitoring for performance and reliability.