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

AI Engineer with 6+ years of experience designing, developing, and deploying Generative AI Applications, LLM-powered platforms, AI agents, and Retrieval-Augmented Generation (RAG) systems for intelligent automation and enterprise use cases. Experienced in prompt engineering, context engineering, LangChain, LangGraph, OpenAI/Azure OpenAI APIs, vector databases, semantic search, and FastAPI-based cloud-native microservices. Proven success building AI copilots, enterprise search platforms, knowledge assistants, document intelligence solutions, and workflow automation systems that improve retrieval accuracy, operational efficiency, response quality, and reliability across business environments through rigorous evaluation, monitoring, and cost/latency optimization.…AI Engineer with 6+ years of experience designing, developing, and deploying Generative AI Applications, LLM-powered platforms, AI agents, and Retrieval-Augmented Generation (RAG) systems for intelligent automation and enterprise use cases. Experienced in prompt engineering, context engineering, LangChain, LangGraph, OpenAI/Azure OpenAI APIs, vector databases, semantic search, and FastAPI-based cloud-native microservices. Proven success building AI copilots, enterprise search platforms, knowledge assistants, document intelligence solutions, and workflow automation systems that improve retrieval accuracy, operational efficiency, response quality, and reliability across business environments through rigorous evaluation, monitoring, and cost/latency optimization.

Kumar Shubham

AI Engineer, AI Developer, Web Developer, +2





AI Engineer with 6+ years of experience designing, developing, and deploying Generative AI Applications, LLM-powered platforms, AI agents, and Retrieval-Augmented Generation (RAG) systems for intelligent automation and enterprise use cases. Experienced in prompt engineering, context engineering, LangChain, LangGraph, OpenAI/Azure OpenAI APIs, vector databases, semantic search, and FastAPI-based cloud-native microservices. Proven success building AI copilots, enterprise search platforms, knowledge assistants, document intelligence solutions, and workflow automation systems that improve retrieval accuracy, operational efficiency, response quality, and reliability across business environments through rigorous evaluation, monitoring, and cost/latency optimization.…AI Engineer with 6+ years of experience designing, developing, and deploying Generative AI Applications, LLM-powered platforms, AI agents, and Retrieval-Augmented Generation (RAG) systems for intelligent automation and enterprise use cases. Experienced in prompt engineering, context engineering, LangChain, LangGraph, OpenAI/Azure OpenAI APIs, vector databases, semantic search, and FastAPI-based cloud-native microservices. Proven success building AI copilots, enterprise search platforms, knowledge assistants, document intelligence solutions, and workflow automation systems that improve retrieval accuracy, operational efficiency, response quality, and reliability across business environments through rigorous evaluation, monitoring, and cost/latency optimization.

Available to hire

AI Engineer with 6+ years of experience designing, developing, and deploying Generative AI Applications, LLM-powered platforms, AI agents, and Retrieval-Augmented Generation (RAG) systems for intelligent automation and enterprise use cases. Experienced in prompt engineering, context engineering, LangChain, LangGraph, OpenAI/Azure OpenAI APIs, vector databases, semantic search, and FastAPI-based cloud-native microservices.

Proven success building AI copilots, enterprise search platforms, knowledge assistants, document intelligence solutions, and workflow automation systems that improve retrieval accuracy, operational efficiency, response quality, and reliability across business environments through rigorous evaluation, monitoring, and cost/latency optimization.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

Work Experience

AI Engineer at Bio World (Zennero)

January 1, 2026 - Present

Developed enterprise-grade AI assistants and AI copilot solutions using OpenAI APIs, LangChain, LangGraph, FastAPI, and Pinecone, reducing retrieval time by 42%. Built RAG platforms processing 250,000+ documents with vector embeddings, semantic search, and contextual retrieval, improving search accuracy by 37%. Designed agentic AI workflows using AI agents, function calling, tool integration, and workflow orchestration to automate business processes and reduce manual effort by 34%. Implemented prompt and context engineering frameworks to increase response consistency by 31% while minimizing hallucinations. Integrated AI applications with enterprise systems via FastAPI microservices and REST APIs, reducing workflow completion time by 29%. Optimized vector retrieval and prompt execution to lower latency by 36% and reduce token usage costs. Established AI observability and evaluation frameworks for retrieval effectiveness, response quality, latency, and reliability, reducing recurring ope

AI Engineer Intern at Capital One Financial

June 1, 2025 - December 1, 2025

Developed LLM-powered enterprise applications using OpenAI APIs, LangChain, Python, and FastAPI, reducing document processing and summarization time by 48%. Built RAG pipelines with vector embeddings, semantic search, and contextual retrieval to improve enterprise search efficiency by 33%. Applied prompt engineering and prompt optimization to improve contextual response accuracy by 29% and reduce low-confidence outputs. Implemented AI workflow orchestration services integrating agents, retrieval pipelines, and enterprise knowledge sources, improving automation efficiency. Created FastAPI-based AI services for intelligent document processing, conversational AI, and enterprise search. Assisted deployment and monitoring using Docker, CI/CD pipelines, and cloud platforms to improve release efficiency and deployment stability.

Software Engineer at GlobalLogic

April 1, 2022 - July 1, 2024

Developed and integrated LLM-powered copilot capabilities using Python, prompt engineering, and generative AI workflows, improving developer productivity by 32%. Built AI-enabled backend services and REST APIs supporting contextual search, document processing, and enterprise workflow automation. Designed prompt engineering and response optimization frameworks to improve contextual relevance and AI-assisted application performance. Implemented semantic search and knowledge retrieval using embedding-based retrieval techniques to improve information accessibility. Built scalable microservices and backend integrations supporting AI-driven business applications and operational analytics. Collaborated in Agile teams to deliver production-ready AI features and enterprise enhancements.

Software Engineer at CGI Inc.

October 1, 2021 - April 1, 2022

Developed enterprise applications using Java, SQL, backend integration frameworks, and AI-assisted automation modules to improve operational efficiency. Built intelligent workflow automation solutions and backend APIs supporting document processing and enterprise modernization initiatives. Optimized SQL queries and data processing workflows to improve API response times by 31%. Supported AI-enabled business automation via enterprise data integration and workflow orchestration. Collaborated with development and QA teams to deploy applications and improve production stability for business-critical systems.

Associate Software Engineer at CGI Inc.

August 1, 2019 - September 1, 2021

Developed workflow management applications supporting insurance operations and claims processing. Assisted backend development using Java, SQL, and REST APIs with database optimization to improve application performance. Supported business process automation and reporting initiatives, reducing manual effort and improving workflow efficiency. Collaborated with cross-functional Agile/Scrum teams on development, testing, and deployment activities.