Open to opportunities

Amresh Yadav

@amreshyadav

Message

Generative AI Engineer specializing in LLM systems, agentic AI workflows, and production MLOps for enterprise impact.

India

Message

What I'm looking for

I’m looking to build production-ready LLM systems and agentic AI workflows that automate real business processes—pairing strong RAG/document intelligence with robust MLOps on Azure/Google Cloud, so teams ship reliably and reduce operational pain.

I’m a Generative AI Engineer with 4+ years of experience designing, developing, and deploying production-grade AI applications across enterprise ITSM and retail analytics domains. I specialize in LLM-powered copilots, Retrieval-Augmented Generation (RAG), and agentic AI workflows—especially document intelligence and enterprise automation.

I’ve delivered solutions that reduce MTTR, automate business workflows, improve forecasting accuracy, and enhance decision-making through production-ready MLOps pipelines. At Tredence Inc., I’m architecting an enterprise conversational demand-forecasting assistant with agentic workflows, and I’ve built systems like Walmart anomaly root-cause analysis and a Wayfair SOP automation platform, leveraging FastAPI, LangGraph, RAG, Docker, Kubernetes, and CI/CD.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist / Generative AI Engineer

Current

Tredence Inc

Sep 2025 - Present (10 months)

Architecting an enterprise conversational, LLM-powered assistant for demand forecasting using Vertex AI, Gemini, Google ADK, and agentic workflows. Built systems for anomaly root-cause analysis and supplier SOP automation, deploying services with FastAPI, Docker, Kubernetes, and CI/CD.

Generative AI LLM Agentic AI Vertex AI Gemini Google ADK LangGraph Retrieval Augmented Generation (RAG)Tool calling Function Calling GPT 4o fastAPI Docker Kubernetes CI CD

Data Scientist

ITC Infotech

Sep 2022 - Sep 2025 (3 years)

Developed enterprise analytics and LLM assistants for ITSM incident analysis, KPI/MTTR insights, and document intelligence, using Azure data pipelines and dashboards. Containerized and deployed GenAI applications with Azure ML and Kubernetes, implementing CI/CD and MLflow-based MLOps for monitoring and governance.