Looking for a job

Mamoon Qazi

@mamoonqazi

Message

I build production LLM applications, RAG chatbots, and scalable MLOps platforms.

India

Message

What I'm looking for

I'm looking to build and deploy production GenAI and LLM applications, including RAG, agentic workflows, and scalable MLOps platforms across cloud environments.

At Ernst & Young GDS, I build AI and data solutions that turn complex documents and workflows into production-ready LLM applications.

I designed a RAG-based chatbot for an insurance client that improved policy-document query accuracy by 35%, and developed domain-specific LLMs for negotiation automation and document generation.

I also built LangChain agent workflows for procurement and an agent-based system that generated validated SQL stored procedures from STM files, reducing development and release time by 40%.

Previously, I architected Azure MLOps pipelines with CI/CD, containerized deployment, and model monitoring, and built autoscaling microservices and APIs for LLM inference workloads.

Experience

Work history, roles, and key accomplishments

Current

Software Engineer (AI and Data)

Current

Ernst & Young GDS

Oct 2023 - Present (2 years 11 months)

Designed and implemented a RAG-based chatbot for an insurance client, improving document query accuracy by 35%. Developed and fine-tuned domain-specific LLMs for negotiation automation and document generation, and built agentic workflow orchestration using LangChain Agents.

RAG Lang Chain LLM Fine tuning Prompt Engineering Transformer Architecture Agentic Workflows SQL Python

Software Engineer (Full Stack Cloud Developer)

Ernst & Young GDS

Aug 2022 - Oct 2023 (1 year 2 months)

Architected MLOps pipelines on Azure integrating CI/CD, containerized deployment, and model monitoring for scalable LLM serving. Developed microservices and APIs for LLM inference workloads with auto-scaling to support production traffic.

Azure MLOps CI CD Docker Kubernetes Microservices API Development LLM Inference

Data Analyst Intern

HighRadius

Jun 2021 - Jul 2021 (1 month)

Played a pivotal role in data handling and analysis for an ML model predicting payment shortfalls. Integrated processed data into the ML pipeline, enabling seamless data flow from EDA to model development and testing.

Data Analysis Machine Learning EDA Python Pandas