P
Prathyush Lebaku
Prathyush Lebaku
About
Detail
Texas, United States
AI Engineer with over 4 years of experience in building Generative AI, RAG, and machine learning solutions for business purposes.
• High level of expertise with LLM models (GPT, Llama), NLP, and deep learning approaches.
• Hands-on experience building agentic AI workflows using LangChain and LangGraph.
• Experience in creating full cycle AI solutions, from data processing and feature engineering to deployment and monitoring of models.
• High-level expertise in developing scalable APIs and microservices by using FastAPI and Flask.
• Experienced in implementing MLOps pipelines, including model versioning, CI/CD, monitoring, and automated retraining.
• Knowledge in creating secure, scalable, and compliance-focused AI systems with robust governance and data privacy controls.
• Experience in developing cloud-native AI solutions on AWS, Azure, and GCP.
• Proven ability to improve model performance, reduce latency, and optimize cost in production environments.
• Extensive knowledge in designing production-level LLM solutions, such as retrieval pipelines, vector databases, and prompt engineering.
• High level of expertise with LLM models (GPT, Llama), NLP, and deep learning approaches.
• Hands-on experience building agentic AI workflows using LangChain and LangGraph.
• Experience in creating full cycle AI solutions, from data processing and feature engineering to deployment and monitoring of models.
• High-level expertise in developing scalable APIs and microservices by using FastAPI and Flask.
• Experienced in implementing MLOps pipelines, including model versioning, CI/CD, monitoring, and automated retraining.
• Knowledge in creating secure, scalable, and compliance-focused AI systems with robust governance and data privacy controls.
• Experience in developing cloud-native AI solutions on AWS, Azure, and GCP.
• Proven ability to improve model performance, reduce latency, and optimize cost in production environments.
• Extensive knowledge in designing production-level LLM solutions, such as retrieval pipelines, vector databases, and prompt engineering.
