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

I am a passionate AI Engineer with over 3 years of hands-on experience designing, developing, and deploying GenAI and LLM applications, including GPT-4, Claude 3, Lang Chain, Llama Index, and Pinecone. I have built retrieval-augmented generation systems, intelligent chatbots, and NLP automation workflows that drive efficiency and reduce manual effort. I am skilled in prompt engineering, model evaluation, vector databases, and API integration, with strong AWS and Docker expertise for scalable cloud deployments. I thrive in Agile environments and apply MLOps best practices to optimize model performance, reliability, and cost efficiency in enterprise settings.…I am a passionate AI Engineer with over 3 years of hands-on experience designing, developing, and deploying GenAI and LLM applications, including GPT-4, Claude 3, Lang Chain, Llama Index, and Pinecone. I have built retrieval-augmented generation systems, intelligent chatbots, and NLP automation workflows that drive efficiency and reduce manual effort. I am skilled in prompt engineering, model evaluation, vector databases, and API integration, with strong AWS and Docker expertise for scalable cloud deployments. I thrive in Agile environments and apply MLOps best practices to optimize model performance, reliability, and cost efficiency in enterprise settings.

Rajesh Tatapudi

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





I am a passionate AI Engineer with over 3 years of hands-on experience designing, developing, and deploying GenAI and LLM applications, including GPT-4, Claude 3, Lang Chain, Llama Index, and Pinecone. I have built retrieval-augmented generation systems, intelligent chatbots, and NLP automation workflows that drive efficiency and reduce manual effort. I am skilled in prompt engineering, model evaluation, vector databases, and API integration, with strong AWS and Docker expertise for scalable cloud deployments. I thrive in Agile environments and apply MLOps best practices to optimize model performance, reliability, and cost efficiency in enterprise settings.…I am a passionate AI Engineer with over 3 years of hands-on experience designing, developing, and deploying GenAI and LLM applications, including GPT-4, Claude 3, Lang Chain, Llama Index, and Pinecone. I have built retrieval-augmented generation systems, intelligent chatbots, and NLP automation workflows that drive efficiency and reduce manual effort. I am skilled in prompt engineering, model evaluation, vector databases, and API integration, with strong AWS and Docker expertise for scalable cloud deployments. I thrive in Agile environments and apply MLOps best practices to optimize model performance, reliability, and cost efficiency in enterprise settings.

Available to hire

I am a passionate AI Engineer with over 3 years of hands-on experience designing, developing, and deploying GenAI and LLM applications, including GPT-4, Claude 3, Lang Chain, Llama Index, and Pinecone. I have built retrieval-augmented generation systems, intelligent chatbots, and NLP automation workflows that drive efficiency and reduce manual effort. I am skilled in prompt engineering, model evaluation, vector databases, and API integration, with strong AWS and Docker expertise for scalable cloud deployments.

I thrive in Agile environments and apply MLOps best practices to optimize model performance, reliability, and cost efficiency in enterprise settings.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Advanced

Work Experience

AI Engineer at Codeium

June 1, 2024 - Present

Designed and deployed retrieval-augmented generation (RAG) architecture using Lang Chain, Pinecone, and Llama Index, improving retrieval precision for enterprise HR systems. Built and optimized LLM prompt pipelines with GPT-4 and Claude 3 to automate resume parsing and candidate-matching workflows, reducing manual review time. Developed zero-shot and few-shot prompt frameworks for job-match scoring and classification; implemented Prompt Layer and Lang Smith for latency tracking and regression benchmarking. Created Streamlit dashboards enabling HR analysts to access GPT-powered insights for candidate recommendations and skill analysis. Deployed containerized RAG pipelines on AWS Lambda with CI/CD via GitHub Actions and Jenkins. Applied caching and API optimization for OpenAI endpoints and conducted A/B testing to refine retrieval accuracy.

AI Engineer at HapivetAI

July 1, 2023 - October 23, 2025

Developed and deployed GPT-3.5 and GPT-4 chatbots for enterprise customer support; built a Retrieval-Augmented Generation (RAG) chatbot using Lang Chain and FAISS on AWS Lambda with sub-two-second latency; designed and optimized system prompts for financial NLP workflows, including entity extraction, summarization, and classification; engineered FastAPI-based microservices for CRM analytics dashboards; implemented emotion and sentiment analysis pipelines using Hugging Face Transformers with custom preprocessing workflows; containerized LLM services with Docker and CI/CD via Jenkins and GitHub Actions; created a Streamlit-based QA interface for prompt testing and latency monitoring; authored internal documentation and best practices for prompt engineering.